[GH-ISSUE #12072] MacOS: GGML_ASSERT(prev != ggml_uncaught_exception) #8019

New Issue

GiteaMirror · 2026-04-12T20:14:38-05:00

GiteaMirror commented

2026-04-12 20:14:38 -05:00

Originally created by @rick-github on GitHub (Aug 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12072

Originally assigned to: @dhiltgen on GitHub.

Sure @rick-github

`
time=2025-08-25T17:28:14.394+03:00 level=INFO source=server.go:383 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 --port 57949"
time=2025-08-25T17:28:14.399+03:00 level=INFO source=server.go:488 msg="system memory" total="16.0 GiB" free="6.3 GiB" free_swap="0 B"
time=2025-08-25T17:28:14.401+03:00 level=INFO source=server.go:531 msg=offload library=cpu layers.requested=-1 layers.model=27 layers.offload=0 layers.split=[] memory.available="[6.4 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.3 GiB" memory.required.partial="0 B" memory.required.kv="38.0 MiB" memory.required.allocations="[1.3 GiB]" memory.weights.total="762.5 MiB" memory.weights.repeating="456.5 MiB" memory.weights.nonrepeating="306.0 MiB" memory.graph.full="514.2 MiB" memory.graph.partial="750.5 MiB"
time=2025-08-25T17:28:14.441+03:00 level=INFO source=runner.go:1006 msg="starting ollama engine"
time=2025-08-25T17:28:14.442+03:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:57949"
time=2025-08-25T17:28:14.446+03:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-08-25T17:28:14.537+03:00 level=INFO source=ggml.go:130 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=340 num_key_values=32
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed
(lldb) process attach --pid 73549
error: attach failed: attach failed (Not allowed to attach to process. Look in the console messages (Console.app), near the debugserver entries, when the attach failed. The subsystem that denied the attach permission will likely have logged an informative message about why it was denied.)
SIGABRT: abort
PC=0x7ff819409846 m=4 sigcode=0
signal arrived during cgo execution

goroutine 9 gp=0xc000505180 m=4 mp=0xc000077808 [syscall]:
runtime.cgocall(0x10fa90cb0, 0xc000046720)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/cgocall.go:167 +0x4b fp=0xc0000466f8 sp=0xc0000466c0 pc=0x10edb488b
github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x6000009938d0)
_cgo_gotypes.go:195 +0x3a fp=0xc000046720 sp=0xc0000466f8 pc=0x10f16145a
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003c094, 0x2b})
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0000467b8 sp=0xc000046720 pc=0x10f160ef5
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1()
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x546 fp=0xc000046a18 sp=0xc0000467b8 pc=0x10f160d46
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046a60 sp=0xc000046a18 pc=0x10f160722
sync.(*Once).doSlow(0x1102103b0?, 0x110ae31a0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046ab8 sp=0xc000046a60 pc=0x10edc9deb
sync.(*Once).Do(0x0?, 0xc000046b60?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046ad8 sp=0xc000046ab8 pc=0x10edc9d19
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046b08 sp=0xc000046ad8 pc=0x10f16068d
github.com/ollama/ollama/ml/backend/ggml.init.func1()
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:44 +0x23 fp=0xc000046b98 sp=0xc000046b08 pc=0x10f1e0803
github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046be0 sp=0xc000046b98 pc=0x10f1e0702
sync.(*Once).doSlow(0x10001102060e8?, 0xc000074088?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046c38 sp=0xc000046be0 pc=0x10edc9deb
sync.(*Once).Do(0x10edc9ea0?, 0x110ae379c?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046c58 sp=0xc000046c38 pc=0x10edc9d19
github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func3()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046c88 sp=0xc000046c58 pc=0x10f1e066d
github.com/ollama/ollama/ml/backend/ggml.New({0x7ff7b11bfae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0})
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:141 +0x124 fp=0xc000047558 sp=0xc000046c88 pc=0x10f1e86e4
github.com/ollama/ollama/ml.NewBackend({0x7ff7b11bfae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0})
/Users/runner/work/ollama/ollama/ml/backend.go:358 +0x9c fp=0xc0000475a8 sp=0xc000047558 pc=0x10f18821c
github.com/ollama/ollama/model.New({0x7ff7b11bfae2?, 0x0?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0})
/Users/runner/work/ollama/ollama/model/model.go:102 +0x7e fp=0xc0000476a0 sp=0xc0000475a8 pc=0x10f1fb53e
github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc0000c25a0, {0x7ff7b11bfae2?, 0x10f0abb1a?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}, {0x0, ...}, ...)
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:854 +0xcc fp=0xc000047730 sp=0xc0000476a0 pc=0x10f2a8a0c
github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc0000c25a0, {0x11020e148, 0xc0001ca460}, 0xc00051a000)
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:952 +0x54d fp=0xc000047ac0 sp=0xc000047730 pc=0x10f2a958d
github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x11020e148?, 0xc0001ca460?}, 0xc0000adb40?)
:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x10f2aad96
net/http.HandlerFunc.ServeHTTP(0xc0000c75c0?, {0x11020e148?, 0xc0001ca460?}, 0xc0000adb60?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x10f0b67e9
net/http.(*ServeMux).ServeHTTP(0x10ed5d3c5?, {0x11020e148, 0xc0001ca460}, 0xc00051a000)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x10f0b86e4
net/http.serverHandler.ServeHTTP({0x11020a7b0?}, {0x11020e148?, 0xc0001ca460?}, 0x1?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x10f0d616e
net/http.(*conn).serve(0xc0000e83f0, {0x1102103e8, 0xc0000ec660})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x10f0b4ce5
net/http.(*Server).Serve.gowrap3()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x10f0ba5a8
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x10edbf7e1
created by net/http.(*Server).Serve in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x485

goroutine 1 gp=0xc000002380 m=nil [IO wait]:
runtime.gopark(0xc0005177e0?, 0x10edda918?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc001605790 sp=0xc001605770 pc=0x10edb7cae
runtime.netpollblock(0xc0005177e0?, 0xed520a6?, 0x1?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0016057c8 sp=0xc001605790 pc=0x10ed7d497
internal/poll.runtime_pollWait(0x1576f4070, 0x72)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc0016057e8 sp=0xc0016057c8 pc=0x10edb6f05
internal/poll.(*pollDesc).wait(0xc0000b9000?, 0x9000ec6c0?, 0x0)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc001605810 sp=0xc0016057e8 pc=0x10ee3c527
internal/poll.(*pollDesc).waitRead(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc0000b9000)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:620 +0x295 fp=0xc0016058b8 sp=0xc001605810 pc=0x10ee418f5
net.(*netFD).accept(0xc0000b9000)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_unix.go:172 +0x29 fp=0xc001605970 sp=0xc0016058b8 pc=0x10eeb57c9
net.(*TCPListener).accept(0xc00004ef40)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock_posix.go:159 +0x1b fp=0xc0016059c0 sp=0xc001605970 pc=0x10eeca45b
net.(*TCPListener).Accept(0xc00004ef40)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock.go:380 +0x30 fp=0xc0016059f0 sp=0xc0016059c0 pc=0x10eec9350
net/http.(*onceCloseListener).Accept(0xc0000e83f0?)
:1 +0x24 fp=0xc001605a08 sp=0xc0016059f0 pc=0x10f0e28e4
net/http.(*Server).Serve(0xc0001f7600, {0x11020df68, 0xc00004ef40})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3424 +0x30c fp=0xc001605b38 sp=0xc001605a08 pc=0x10f0ba1ac
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc000138030, 0x4, 0x4})
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1044 +0x8c6 fp=0xc001605d08 sp=0xc001605b38 pc=0x10f2aa766
github.com/ollama/ollama/runner.Execute({0xc000138010?, 0x0?, 0x0?})
/Users/runner/work/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc001605d30 sp=0xc001605d08 pc=0x10f2aafa9
github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f7400?, {0x10fd7e098?, 0x4?, 0x10fd7e09c?})
/Users/runner/work/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc001605d58 sp=0xc001605d30 pc=0x10fa10525
github.com/spf13/cobra.(*Command).execute(0xc0000eef08, {0xc0000bae60, 0x5, 0x5})
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc001605e78 sp=0xc001605d58 pc=0x10ef2df1c
github.com/spf13/cobra.(*Command).ExecuteC(0xc000496f08)
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc001605f30 sp=0xc001605e78 pc=0x10ef2e765
github.com/spf13/cobra.(*Command).Execute(...)
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
/Users/runner/work/ollama/ollama/main.go:12 +0x4d fp=0xc001605f50 sp=0xc001605f30 pc=0x10fa1100d
runtime.main()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:283 +0x28b fp=0xc001605fe0 sp=0xc001605f50 pc=0x10ed841cb
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc001605fe8 sp=0xc001605fe0 pc=0x10edbf7e1

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070fa8 sp=0xc000070f88 pc=0x10edb7cae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.forcegchelper()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:348 +0xb3 fp=0xc000070fe0 sp=0xc000070fa8 pc=0x10ed84513
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x10edbf7e1
created by runtime.init.7 in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071780 sp=0xc000071760 pc=0x10edb7cae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.bgsweep(0xc00009c000)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcsweep.go:316 +0xdf fp=0xc0000717c8 sp=0xc000071780 pc=0x10ed6f63f
runtime.gcenable.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x25 fp=0xc0000717e0 sp=0xc0000717c8 pc=0x10ed63a85
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000717e8 sp=0xc0000717e0 pc=0x10edbf7e1
created by runtime.gcenable in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x10ff3b6a8?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071f78 sp=0xc000071f58 pc=0x10edb7cae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.(*scavengerState).park(0x110ab9ee0)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:425 +0x49 fp=0xc000071fa8 sp=0xc000071f78 pc=0x10ed6d069
runtime.bgscavenge(0xc00009c000)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:658 +0x59 fp=0xc000071fc8 sp=0xc000071fa8 pc=0x10ed6d5f9
runtime.gcenable.gowrap2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x10ed63a25
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x10edbf7e1
created by runtime.gcenable in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0xa5

goroutine 18 gp=0xc000102700 m=nil [finalizer wait]:
runtime.gopark(0x1b8?, 0x10ed865e7?, 0x1?, 0x23?, 0xc000070688?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070630 sp=0xc000070610 pc=0x10edb7cae
runtime.runfinq()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:196 +0x107 fp=0xc0000707e0 sp=0xc000070630 pc=0x10ed62a47
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x10edbf7e1
created by runtime.createfing in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:166 +0x3d

goroutine 19 gp=0xc000103180 m=nil [chan receive]:
runtime.gopark(0xc0002297c0?, 0xc000010048?, 0x60?, 0xc7?, 0x10ee981c8?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006c718 sp=0xc00006c6f8 pc=0x10edb7cae
runtime.chanrecv(0xc000110310, 0x0, 0x1)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:664 +0x445 fp=0xc00006c790 sp=0xc00006c718 pc=0x10ed54845
runtime.chanrecv1(0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:506 +0x12 fp=0xc00006c7b8 sp=0xc00006c790 pc=0x10ed543d2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1799 +0x2f fp=0xc00006c7e0 sp=0xc00006c7b8 pc=0x10ed66bcf
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x10edbf7e1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1794 +0x79

goroutine 20 gp=0xc000103500 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006cf38 sp=0xc00006cf18 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006cfc8 sp=0xc00006cf38 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006cfe0 sp=0xc00006cfc8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
runtime.gopark(0xbc335d31ca6?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]:
runtime.gopark(0xbc336491363?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000072738 sp=0xc000072718 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc0000727c8 sp=0xc000072738 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc0000727e0 sp=0xc0000727c8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle)]:
runtime.gopark(0xbc335d319e1?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006d738 sp=0xc00006d718 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006d7c8 sp=0xc00006d738 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0xbc335d37da0?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]:
runtime.gopark(0xbc335d321c0?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle)]:
runtime.gopark(0xbc33663a71c?, 0x1?, 0xb6?, 0xda?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000072f38 sp=0xc000072f18 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000072fc8 sp=0xc000072f38 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc000072fe0 sp=0xc000072fc8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 7 gp=0xc000003dc0 m=nil [GC worker (idle)]:
runtime.gopark(0xbc336576ba9?, 0x3?, 0xd7?, 0x24?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000073738 sp=0xc000073718 pc=0x10edb7cae
runtime.gcBgMarkWorker(0xc000111730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc0000737c8 sp=0xc000073738 pc=0x10ed65ee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x10ed65dc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x10edbf7e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc000504fc0 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0x20?, 0x21?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050d6d0 sp=0xc00050d6b0 pc=0x10edb7cae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.semacquire1(0xc0000c2658, 0x0, 0x1, 0x0, 0x18)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:188 +0x21d fp=0xc00050d738 sp=0xc00050d6d0 pc=0x10ed9769d
sync.runtime_SemacquireWaitGroup(0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:110 +0x25 fp=0xc00050d770 sp=0xc00050d738 pc=0x10edb9645
sync.(*WaitGroup).Wait(0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/waitgroup.go:118 +0x48 fp=0xc00050d798 sp=0xc00050d770 pc=0x10edcb228
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0000c25a0, {0x110210420, 0xc0000baf00})
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:366 +0x2a fp=0xc00050d7b8 sp=0xc00050d798 pc=0x10f2a498a
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x28 fp=0xc00050d7e0 sp=0xc00050d7b8 pc=0x10f2aa9c8
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050d7e8 sp=0xc00050d7e0 pc=0x10edbf7e1
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x4c9

goroutine 37 gp=0xc000002000 m=nil [IO wait]:
runtime.gopark(0x5?, 0xc0000ec761?, 0x1?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000507dd8 sp=0xc000507db8 pc=0x10edb7cae
runtime.netpollblock(0x10edd9665?, 0xed520a6?, 0x1?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc000507e10 sp=0xc000507dd8 pc=0x10ed7d497
internal/poll.runtime_pollWait(0x1576f3f58, 0x72)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc000507e30 sp=0xc000507e10 pc=0x10edb6f05
internal/poll.(*pollDesc).wait(0xc0000b9080?, 0xc0000ec761?, 0x0)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000507e58 sp=0xc000507e30 pc=0x10ee3c527
internal/poll.(*pollDesc).waitRead(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc0000b9080, {0xc0000ec761, 0x1, 0x1})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:165 +0x27a fp=0xc000507ef0 sp=0xc000507e58 pc=0x10ee3d81a
net.(*netFD).Read(0xc0000b9080, {0xc0000ec761?, 0x0?, 0x0?})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_posix.go:55 +0x25 fp=0xc000507f38 sp=0xc000507ef0 pc=0x10eeb3825
net.(*conn).Read(0xc00011c908, {0xc0000ec761?, 0x0?, 0x0?})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/net.go:194 +0x45 fp=0xc000507f80 sp=0xc000507f38 pc=0x10eec12c5
net/http.(*connReader).backgroundRead(0xc0000ec750)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:690 +0x37 fp=0xc000507fc8 sp=0xc000507f80 pc=0x10f0aebb7
net/http.(*connReader).startBackgroundRead.gowrap2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0x25 fp=0xc000507fe0 sp=0xc000507fc8 pc=0x10f0aeae5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000507fe8 sp=0xc000507fe0 pc=0x10edbf7e1
created by net/http.(*connReader).startBackgroundRead in goroutine 9
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0xb6

rax 0x0
rbx 0x6
rcx 0x700003d838b8
rdx 0x0
rdi 0x1c03
rsi 0x6
rbp 0x700003d838e0
rsp 0x700003d838b8
r8 0xd4b00000000
r9 0x160300000003
r10 0x7ff85b0519c0
r11 0x246
r12 0x7b9
r13 0x157a932a0
r14 0x1c03
r15 0x16
rip 0x7ff819409846
rflags 0x246
cs 0x7
fs 0x0
gs 0x0
time=2025-08-25T17:28:15.631+03:00 level=ERROR source=server.go:409 msg="llama runner terminated" error="exit status 2"
time=2025-08-25T17:28:15.631+03:00 level=INFO source=sched.go:441 msg="Load failed" model=/Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 error="do load request: Post "http://127.0.0.1:57949/load": EOF"
[GIN] 2025/08/25 - 17:28:15 | 500 | 1.74070275s | 127.0.0.1 | POST "/api/generate"
time=2025-08-25T17:28:38.634+03:00 level=INFO source=server.go:383 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 --port 57971"
time=2025-08-25T17:28:38.640+03:00 level=INFO source=server.go:488 msg="system memory" total="16.0 GiB" free="5.8 GiB" free_swap="0 B"
time=2025-08-25T17:28:38.641+03:00 level=INFO source=server.go:531 msg=offload library=cpu layers.requested=-1 layers.model=27 layers.offload=0 layers.split=[] memory.available="[5.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.3 GiB" memory.required.partial="0 B" memory.required.kv="38.0 MiB" memory.required.allocations="[1.3 GiB]" memory.weights.total="762.5 MiB" memory.weights.repeating="456.5 MiB" memory.weights.nonrepeating="306.0 MiB" memory.graph.full="514.2 MiB" memory.graph.partial="750.5 MiB"
time=2025-08-25T17:28:38.668+03:00 level=INFO source=runner.go:1006 msg="starting ollama engine"
time=2025-08-25T17:28:38.668+03:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:57971"
time=2025-08-25T17:28:38.675+03:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-08-25T17:28:38.762+03:00 level=INFO source=ggml.go:130 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=340 num_key_values=32
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed
(lldb) process attach --pid 73757
error: attach failed: attach failed (Not allowed to attach to process. Look in the console messages (Console.app), near the debugserver entries, when the attach failed. The subsystem that denied the attach permission will likely have logged an informative message about why it was denied.)
SIGABRT: abort
PC=0x7ff819409846 m=6 sigcode=0
signal arrived during cgo execution

goroutine 7 gp=0xc000584c40 m=6 mp=0xc000180008 [syscall]:
runtime.cgocall(0x10feb8cb0, 0xc000046720)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/cgocall.go:167 +0x4b fp=0xc0000466f8 sp=0xc0000466c0 pc=0x10f1dc88b
github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x6000019f0840)
_cgo_gotypes.go:195 +0x3a fp=0xc000046720 sp=0xc0000466f8 pc=0x10f58945a
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003c094, 0x2b})
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0000467b8 sp=0xc000046720 pc=0x10f588ef5
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1()
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x546 fp=0xc000046a18 sp=0xc0000467b8 pc=0x10f588d46
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046a60 sp=0xc000046a18 pc=0x10f588722
sync.(*Once).doSlow(0x1106383b0?, 0x110f0b1a0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046ab8 sp=0xc000046a60 pc=0x10f1f1deb
sync.(*Once).Do(0x0?, 0xc000046b60?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046ad8 sp=0xc000046ab8 pc=0x10f1f1d19
github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046b08 sp=0xc000046ad8 pc=0x10f58868d
github.com/ollama/ollama/ml/backend/ggml.init.func1()
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:44 +0x23 fp=0xc000046b98 sp=0xc000046b08 pc=0x10f608803
github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046be0 sp=0xc000046b98 pc=0x10f608702
sync.(*Once).doSlow(0x100011062e0e8?, 0xc000074618?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046c38 sp=0xc000046be0 pc=0x10f1f1deb
sync.(*Once).Do(0x10f1f1ea0?, 0x110f0b79c?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046c58 sp=0xc000046c38 pc=0x10f1f1d19
github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func3()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046c88 sp=0xc000046c58 pc=0x10f60866d
github.com/ollama/ollama/ml/backend/ggml.New({0x7ff7b0d97ae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0})
/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:141 +0x124 fp=0xc000047558 sp=0xc000046c88 pc=0x10f6106e4
github.com/ollama/ollama/ml.NewBackend({0x7ff7b0d97ae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0})
/Users/runner/work/ollama/ollama/ml/backend.go:358 +0x9c fp=0xc0000475a8 sp=0xc000047558 pc=0x10f5b021c
github.com/ollama/ollama/model.New({0x7ff7b0d97ae2?, 0x0?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0})
/Users/runner/work/ollama/ollama/model/model.go:102 +0x7e fp=0xc0000476a0 sp=0xc0000475a8 pc=0x10f62353e
github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc0002a8d20, {0x7ff7b0d97ae2?, 0x10f4d3b1a?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}, {0x0, ...}, ...)
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:854 +0xcc fp=0xc000047730 sp=0xc0000476a0 pc=0x10f6d0a0c
github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc0002a8d20, {0x110636148, 0xc00024ab60}, 0xc0000e6f00)
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:952 +0x54d fp=0xc000047ac0 sp=0xc000047730 pc=0x10f6d158d
github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x110636148?, 0xc00024ab60?}, 0xc000115b40?)
:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x10f6d2d96
net/http.HandlerFunc.ServeHTTP(0xc0000e4300?, {0x110636148?, 0xc00024ab60?}, 0xc000115b60?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x10f4de7e9
net/http.(*ServeMux).ServeHTTP(0x10f1853c5?, {0x110636148, 0xc00024ab60}, 0xc0000e6f00)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x10f4e06e4
net/http.serverHandler.ServeHTTP({0x1106327b0?}, {0x110636148?, 0xc00024ab60?}, 0x1?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x10f4fe16e
net/http.(*conn).serve(0xc0000f43f0, {0x1106383e8, 0xc0000f8660})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x10f4dcce5
net/http.(*Server).Serve.gowrap3()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x10f4e25a8
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x10f1e77e1
created by net/http.(*Server).Serve in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x485

goroutine 1 gp=0xc000002380 m=nil [IO wait]:
runtime.gopark(0xc0005957e0?, 0x10f202918?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc001585790 sp=0xc001585770 pc=0x10f1dfcae
runtime.netpollblock(0xc0005957e0?, 0xf17a0a6?, 0x1?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0015857c8 sp=0xc001585790 pc=0x10f1a5497
internal/poll.runtime_pollWait(0x157cfb830, 0x72)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc0015857e8 sp=0xc0015857c8 pc=0x10f1def05
internal/poll.(*pollDesc).wait(0xc000633100?, 0x9000f86c0?, 0x0)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc001585810 sp=0xc0015857e8 pc=0x10f264527
internal/poll.(*pollDesc).waitRead(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc000633100)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:620 +0x295 fp=0xc0015858b8 sp=0xc001585810 pc=0x10f2698f5
net.(*netFD).accept(0xc000633100)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_unix.go:172 +0x29 fp=0xc001585970 sp=0xc0015858b8 pc=0x10f2dd7c9
net.(*TCPListener).accept(0xc00004ee00)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock_posix.go:159 +0x1b fp=0xc0015859c0 sp=0xc001585970 pc=0x10f2f245b
net.(*TCPListener).Accept(0xc00004ee00)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock.go:380 +0x30 fp=0xc0015859f0 sp=0xc0015859c0 pc=0x10f2f1350
net/http.(*onceCloseListener).Accept(0xc0000f43f0?)
:1 +0x24 fp=0xc001585a08 sp=0xc0015859f0 pc=0x10f50a8e4
net/http.(*Server).Serve(0xc000277600, {0x110635f68, 0xc00004ee00})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3424 +0x30c fp=0xc001585b38 sp=0xc001585a08 pc=0x10f4e21ac
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0001b8030, 0x4, 0x4})
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1044 +0x8c6 fp=0xc001585d08 sp=0xc001585b38 pc=0x10f6d2766
github.com/ollama/ollama/runner.Execute({0xc0001b8010?, 0x0?, 0x0?})
/Users/runner/work/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc001585d30 sp=0xc001585d08 pc=0x10f6d2fa9
github.com/ollama/ollama/cmd.NewCLI.func2(0xc000277400?, {0x1101a6098?, 0x4?, 0x1101a609c?})
/Users/runner/work/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc001585d58 sp=0xc001585d30 pc=0x10fe38525
github.com/spf13/cobra.(*Command).execute(0xc0000fcf08, {0xc0000bcb90, 0x5, 0x5})
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc001585e78 sp=0xc001585d58 pc=0x10f355f1c
github.com/spf13/cobra.(*Command).ExecuteC(0xc000642908)
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc001585f30 sp=0xc001585e78 pc=0x10f356765
github.com/spf13/cobra.(*Command).Execute(...)
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
/Users/runner/work/ollama/ollama/main.go:12 +0x4d fp=0xc001585f50 sp=0xc001585f30 pc=0x10fe3900d
runtime.main()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:283 +0x28b fp=0xc001585fe0 sp=0xc001585f50 pc=0x10f1ac1cb
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc001585fe8 sp=0xc001585fe0 pc=0x10f1e77e1

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070fa8 sp=0xc000070f88 pc=0x10f1dfcae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.forcegchelper()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:348 +0xb3 fp=0xc000070fe0 sp=0xc000070fa8 pc=0x10f1ac513
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x10f1e77e1
created by runtime.init.7 in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071780 sp=0xc000071760 pc=0x10f1dfcae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.bgsweep(0xc00009c000)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcsweep.go:316 +0xdf fp=0xc0000717c8 sp=0xc000071780 pc=0x10f19763f
runtime.gcenable.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x25 fp=0xc0000717e0 sp=0xc0000717c8 pc=0x10f18ba85
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000717e8 sp=0xc0000717e0 pc=0x10f1e77e1
created by runtime.gcenable in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x1103636a8?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071f78 sp=0xc000071f58 pc=0x10f1dfcae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.(*scavengerState).park(0x110ee1ee0)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:425 +0x49 fp=0xc000071fa8 sp=0xc000071f78 pc=0x10f195069
runtime.bgscavenge(0xc00009c000)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:658 +0x59 fp=0xc000071fc8 sp=0xc000071fa8 pc=0x10f1955f9
runtime.gcenable.gowrap2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x10f18ba25
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x10f1e77e1
created by runtime.gcenable in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0xa5

goroutine 18 gp=0xc000182700 m=nil [finalizer wait]:
runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000070688?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070630 sp=0xc000070610 pc=0x10f1dfcae
runtime.runfinq()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:196 +0x107 fp=0xc0000707e0 sp=0xc000070630 pc=0x10f18aa47
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x10f1e77e1
created by runtime.createfing in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:166 +0x3d

goroutine 19 gp=0xc000183180 m=nil [chan receive]:
runtime.gopark(0xc0002c50e0?, 0xc000010060?, 0x60?, 0xc7?, 0x10f2c01c8?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006c718 sp=0xc00006c6f8 pc=0x10f1dfcae
runtime.chanrecv(0xc000192310, 0x0, 0x1)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:664 +0x445 fp=0xc00006c790 sp=0xc00006c718 pc=0x10f17c845
runtime.chanrecv1(0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:506 +0x12 fp=0xc00006c7b8 sp=0xc00006c790 pc=0x10f17c3d2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1799 +0x2f fp=0xc00006c7e0 sp=0xc00006c7b8 pc=0x10f18ebcf
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x10f1e77e1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1794 +0x79

goroutine 20 gp=0xc0001836c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006cf38 sp=0xc00006cf18 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006cfc8 sp=0xc00006cf38 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006cfe0 sp=0xc00006cfc8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc000183880 m=nil [GC worker (idle)]:
runtime.gopark(0xbc8d995c01e?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006d738 sp=0xc00006d718 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006d7c8 sp=0xc00006d738 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000584000 m=nil [GC worker (idle)]:
runtime.gopark(0xbc8d995c452?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058a738 sp=0xc00058a718 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00058a7c8 sp=0xc00058a738 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00058a7e0 sp=0xc00058a7c8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058a7e8 sp=0xc00058a7e0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc0005841c0 m=nil [GC worker (idle)]:
runtime.gopark(0xbc8d995e30f?, 0x0?, 0x0?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058af38 sp=0xc00058af18 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00058afc8 sp=0xc00058af38 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00058afe0 sp=0xc00058afc8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058afe8 sp=0xc00058afe0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]:
runtime.gopark(0xbc8d995c8c9?, 0x1?, 0xfa?, 0x7c?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000072738 sp=0xc000072718 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc0000727c8 sp=0xc000072738 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc0000727e0 sp=0xc0000727c8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 22 gp=0xc000183a40 m=nil [GC worker (idle)]:
runtime.gopark(0xbc8d995bfdd?, 0x3?, 0xd?, 0xdc?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006df38 sp=0xc00006df18 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006dfc8 sp=0xc00006df38 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 23 gp=0xc000183c00 m=nil [GC worker (idle)]:
runtime.gopark(0xbc8d995c0db?, 0x1?, 0xe9?, 0x1b?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000584380 m=nil [GC worker (idle)]:
runtime.gopark(0xbc8da2ecdfa?, 0x1?, 0x9b?, 0x1a?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058b738 sp=0xc00058b718 pc=0x10f1dfcae
runtime.gcBgMarkWorker(0xc000193730)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00058b7c8 sp=0xc00058b738 pc=0x10f18dee9
runtime.gcBgMarkStartWorkers.gowrap1()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00058b7e0 sp=0xc00058b7c8 pc=0x10f18ddc5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058b7e8 sp=0xc00058b7e0 pc=0x10f1e77e1
created by runtime.gcBgMarkStartWorkers in goroutine 1
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105

goroutine 6 gp=0xc000584a80 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0x80?, 0x1?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058d6d0 sp=0xc00058d6b0 pc=0x10f1dfcae
runtime.goparkunlock(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441
runtime.semacquire1(0xc0002a8dd8, 0x0, 0x1, 0x0, 0x18)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:188 +0x21d fp=0xc00058d738 sp=0xc00058d6d0 pc=0x10f1bf69d
sync.runtime_SemacquireWaitGroup(0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:110 +0x25 fp=0xc00058d770 sp=0xc00058d738 pc=0x10f1e1645
sync.(*WaitGroup).Wait(0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/waitgroup.go:118 +0x48 fp=0xc00058d798 sp=0xc00058d770 pc=0x10f1f3228
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002a8d20, {0x110638420, 0xc0000bcc30})
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:366 +0x2a fp=0xc00058d7b8 sp=0xc00058d798 pc=0x10f6cc98a
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x28 fp=0xc00058d7e0 sp=0xc00058d7b8 pc=0x10f6d29c8
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058d7e8 sp=0xc00058d7e0 pc=0x10f1e77e1
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x4c9

goroutine 9 gp=0xc000584e00 m=nil [IO wait]:
runtime.gopark(0x5?, 0xc0000f8761?, 0x1?, 0x0?, 0x0?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058ddd8 sp=0xc00058ddb8 pc=0x10f1dfcae
runtime.netpollblock(0x10f201665?, 0xf17a0a6?, 0x1?)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc00058de10 sp=0xc00058ddd8 pc=0x10f1a5497
internal/poll.runtime_pollWait(0x157cfb718, 0x72)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc00058de30 sp=0xc00058de10 pc=0x10f1def05
internal/poll.(*pollDesc).wait(0xc000633180?, 0xc0000f8761?, 0x0)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00058de58 sp=0xc00058de30 pc=0x10f264527
internal/poll.(*pollDesc).waitRead(...)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc000633180, {0xc0000f8761, 0x1, 0x1})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:165 +0x27a fp=0xc00058def0 sp=0xc00058de58 pc=0x10f26581a
net.(*netFD).Read(0xc000633180, {0xc0000f8761?, 0xc00004eed8?, 0xc00058df70?})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_posix.go:55 +0x25 fp=0xc00058df38 sp=0xc00058def0 pc=0x10f2db825
net.(*conn).Read(0xc000074598, {0xc0000f8761?, 0x0?, 0x0?})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/net.go:194 +0x45 fp=0xc00058df80 sp=0xc00058df38 pc=0x10f2e92c5
net/http.(*connReader).backgroundRead(0xc0000f8750)
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:690 +0x37 fp=0xc00058dfc8 sp=0xc00058df80 pc=0x10f4d6bb7
net/http.(*connReader).startBackgroundRead.gowrap2()
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0x25 fp=0xc00058dfe0 sp=0xc00058dfc8 pc=0x10f4d6ae5
runtime.goexit({})
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058dfe8 sp=0xc00058dfe0 pc=0x10f1e77e1
created by net/http.(*connReader).startBackgroundRead in goroutine 7
/Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0xb6

rax 0x0
rbx 0x6
rcx 0x7000032718b8
rdx 0x0
rdi 0x1b03
rsi 0x6
rbp 0x7000032718e0
rsp 0x7000032718b8
r8 0xd4b00000000
r9 0x180300000003
r10 0x7ff85b0519c0
r11 0x246
r12 0x7b9
r13 0x157ebb2a0
r14 0x1b03
r15 0x16
rip 0x7ff819409846
rflags 0x246
cs 0x7
fs 0x0
gs 0x0
time=2025-08-25T17:28:39.242+03:00 level=ERROR source=server.go:409 msg="llama runner terminated" error="exit status 2"
time=2025-08-25T17:28:39.242+03:00 level=INFO source=sched.go:441 msg="Load failed" model=/Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 error="do load request: Post "http://127.0.0.1:57971/load": EOF"
[GIN] 2025/08/25 - 17:28:39 | 500 | 1.014162474s | 127.0.0.1 | POST "/api/generate"
`

Originally posted by @nire0510 in #12025

Originally created by @rick-github on GitHub (Aug 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12072 Originally assigned to: @dhiltgen on GitHub. > Sure @rick-github > > ` > time=2025-08-25T17:28:14.394+03:00 level=INFO source=server.go:383 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 --port 57949" > time=2025-08-25T17:28:14.399+03:00 level=INFO source=server.go:488 msg="system memory" total="16.0 GiB" free="6.3 GiB" free_swap="0 B" > time=2025-08-25T17:28:14.401+03:00 level=INFO source=server.go:531 msg=offload library=cpu layers.requested=-1 layers.model=27 layers.offload=0 layers.split=[] memory.available="[6.4 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.3 GiB" memory.required.partial="0 B" memory.required.kv="38.0 MiB" memory.required.allocations="[1.3 GiB]" memory.weights.total="762.5 MiB" memory.weights.repeating="456.5 MiB" memory.weights.nonrepeating="306.0 MiB" memory.graph.full="514.2 MiB" memory.graph.partial="750.5 MiB" > time=2025-08-25T17:28:14.441+03:00 level=INFO source=runner.go:1006 msg="starting ollama engine" > time=2025-08-25T17:28:14.442+03:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:57949" > time=2025-08-25T17:28:14.446+03:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" > time=2025-08-25T17:28:14.537+03:00 level=INFO source=ggml.go:130 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=340 num_key_values=32 > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed > (lldb) process attach --pid 73549 > error: attach failed: attach failed (Not allowed to attach to process. Look in the console messages (Console.app), near the debugserver entries, when the attach failed. The subsystem that denied the attach permission will likely have logged an informative message about why it was denied.) > SIGABRT: abort > PC=0x7ff819409846 m=4 sigcode=0 > signal arrived during cgo execution > > goroutine 9 gp=0xc000505180 m=4 mp=0xc000077808 [syscall]: > runtime.cgocall(0x10fa90cb0, 0xc000046720) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/cgocall.go:167 +0x4b fp=0xc0000466f8 sp=0xc0000466c0 pc=0x10edb488b > github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x6000009938d0) > _cgo_gotypes.go:195 +0x3a fp=0xc000046720 sp=0xc0000466f8 pc=0x10f16145a > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003c094, 0x2b}) > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0000467b8 sp=0xc000046720 pc=0x10f160ef5 > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1() > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x546 fp=0xc000046a18 sp=0xc0000467b8 pc=0x10f160d46 > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046a60 sp=0xc000046a18 pc=0x10f160722 > sync.(*Once).doSlow(0x1102103b0?, 0x110ae31a0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046ab8 sp=0xc000046a60 pc=0x10edc9deb > sync.(*Once).Do(0x0?, 0xc000046b60?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046ad8 sp=0xc000046ab8 pc=0x10edc9d19 > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046b08 sp=0xc000046ad8 pc=0x10f16068d > github.com/ollama/ollama/ml/backend/ggml.init.func1() > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:44 +0x23 fp=0xc000046b98 sp=0xc000046b08 pc=0x10f1e0803 > github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046be0 sp=0xc000046b98 pc=0x10f1e0702 > sync.(*Once).doSlow(0x10001102060e8?, 0xc000074088?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046c38 sp=0xc000046be0 pc=0x10edc9deb > sync.(*Once).Do(0x10edc9ea0?, 0x110ae379c?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046c58 sp=0xc000046c38 pc=0x10edc9d19 > github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func3() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046c88 sp=0xc000046c58 pc=0x10f1e066d > github.com/ollama/ollama/ml/backend/ggml.New({0x7ff7b11bfae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}) > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:141 +0x124 fp=0xc000047558 sp=0xc000046c88 pc=0x10f1e86e4 > github.com/ollama/ollama/ml.NewBackend({0x7ff7b11bfae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}) > /Users/runner/work/ollama/ollama/ml/backend.go:358 +0x9c fp=0xc0000475a8 sp=0xc000047558 pc=0x10f18821c > github.com/ollama/ollama/model.New({0x7ff7b11bfae2?, 0x0?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}) > /Users/runner/work/ollama/ollama/model/model.go:102 +0x7e fp=0xc0000476a0 sp=0xc0000475a8 pc=0x10f1fb53e > github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc0000c25a0, {0x7ff7b11bfae2?, 0x10f0abb1a?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}, {0x0, ...}, ...) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:854 +0xcc fp=0xc000047730 sp=0xc0000476a0 pc=0x10f2a8a0c > github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc0000c25a0, {0x11020e148, 0xc0001ca460}, 0xc00051a000) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:952 +0x54d fp=0xc000047ac0 sp=0xc000047730 pc=0x10f2a958d > github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x11020e148?, 0xc0001ca460?}, 0xc0000adb40?) > <autogenerated>:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x10f2aad96 > net/http.HandlerFunc.ServeHTTP(0xc0000c75c0?, {0x11020e148?, 0xc0001ca460?}, 0xc0000adb60?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x10f0b67e9 > net/http.(*ServeMux).ServeHTTP(0x10ed5d3c5?, {0x11020e148, 0xc0001ca460}, 0xc00051a000) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x10f0b86e4 > net/http.serverHandler.ServeHTTP({0x11020a7b0?}, {0x11020e148?, 0xc0001ca460?}, 0x1?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x10f0d616e > net/http.(*conn).serve(0xc0000e83f0, {0x1102103e8, 0xc0000ec660}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x10f0b4ce5 > net/http.(*Server).Serve.gowrap3() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x10f0ba5a8 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x10edbf7e1 > created by net/http.(*Server).Serve in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x485 > > goroutine 1 gp=0xc000002380 m=nil [IO wait]: > runtime.gopark(0xc0005177e0?, 0x10edda918?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc001605790 sp=0xc001605770 pc=0x10edb7cae > runtime.netpollblock(0xc0005177e0?, 0xed520a6?, 0x1?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0016057c8 sp=0xc001605790 pc=0x10ed7d497 > internal/poll.runtime_pollWait(0x1576f4070, 0x72) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc0016057e8 sp=0xc0016057c8 pc=0x10edb6f05 > internal/poll.(*pollDesc).wait(0xc0000b9000?, 0x9000ec6c0?, 0x0) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc001605810 sp=0xc0016057e8 pc=0x10ee3c527 > internal/poll.(*pollDesc).waitRead(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89 > internal/poll.(*FD).Accept(0xc0000b9000) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:620 +0x295 fp=0xc0016058b8 sp=0xc001605810 pc=0x10ee418f5 > net.(*netFD).accept(0xc0000b9000) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_unix.go:172 +0x29 fp=0xc001605970 sp=0xc0016058b8 pc=0x10eeb57c9 > net.(*TCPListener).accept(0xc00004ef40) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock_posix.go:159 +0x1b fp=0xc0016059c0 sp=0xc001605970 pc=0x10eeca45b > net.(*TCPListener).Accept(0xc00004ef40) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock.go:380 +0x30 fp=0xc0016059f0 sp=0xc0016059c0 pc=0x10eec9350 > net/http.(*onceCloseListener).Accept(0xc0000e83f0?) > <autogenerated>:1 +0x24 fp=0xc001605a08 sp=0xc0016059f0 pc=0x10f0e28e4 > net/http.(*Server).Serve(0xc0001f7600, {0x11020df68, 0xc00004ef40}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3424 +0x30c fp=0xc001605b38 sp=0xc001605a08 pc=0x10f0ba1ac > github.com/ollama/ollama/runner/ollamarunner.Execute({0xc000138030, 0x4, 0x4}) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1044 +0x8c6 fp=0xc001605d08 sp=0xc001605b38 pc=0x10f2aa766 > github.com/ollama/ollama/runner.Execute({0xc000138010?, 0x0?, 0x0?}) > /Users/runner/work/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc001605d30 sp=0xc001605d08 pc=0x10f2aafa9 > github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f7400?, {0x10fd7e098?, 0x4?, 0x10fd7e09c?}) > /Users/runner/work/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc001605d58 sp=0xc001605d30 pc=0x10fa10525 > github.com/spf13/cobra.(*Command).execute(0xc0000eef08, {0xc0000bae60, 0x5, 0x5}) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc001605e78 sp=0xc001605d58 pc=0x10ef2df1c > github.com/spf13/cobra.(*Command).ExecuteC(0xc000496f08) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc001605f30 sp=0xc001605e78 pc=0x10ef2e765 > github.com/spf13/cobra.(*Command).Execute(...) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992 > github.com/spf13/cobra.(*Command).ExecuteContext(...) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 > main.main() > /Users/runner/work/ollama/ollama/main.go:12 +0x4d fp=0xc001605f50 sp=0xc001605f30 pc=0x10fa1100d > runtime.main() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:283 +0x28b fp=0xc001605fe0 sp=0xc001605f50 pc=0x10ed841cb > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc001605fe8 sp=0xc001605fe0 pc=0x10edbf7e1 > > goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: > runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070fa8 sp=0xc000070f88 pc=0x10edb7cae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.forcegchelper() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:348 +0xb3 fp=0xc000070fe0 sp=0xc000070fa8 pc=0x10ed84513 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x10edbf7e1 > created by runtime.init.7 in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:336 +0x1a > > goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: > runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071780 sp=0xc000071760 pc=0x10edb7cae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.bgsweep(0xc00009c000) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcsweep.go:316 +0xdf fp=0xc0000717c8 sp=0xc000071780 pc=0x10ed6f63f > runtime.gcenable.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x25 fp=0xc0000717e0 sp=0xc0000717c8 pc=0x10ed63a85 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000717e8 sp=0xc0000717e0 pc=0x10edbf7e1 > created by runtime.gcenable in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x66 > > goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: > runtime.gopark(0x10000?, 0x10ff3b6a8?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071f78 sp=0xc000071f58 pc=0x10edb7cae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.(*scavengerState).park(0x110ab9ee0) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:425 +0x49 fp=0xc000071fa8 sp=0xc000071f78 pc=0x10ed6d069 > runtime.bgscavenge(0xc00009c000) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:658 +0x59 fp=0xc000071fc8 sp=0xc000071fa8 pc=0x10ed6d5f9 > runtime.gcenable.gowrap2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x10ed63a25 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x10edbf7e1 > created by runtime.gcenable in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0xa5 > > goroutine 18 gp=0xc000102700 m=nil [finalizer wait]: > runtime.gopark(0x1b8?, 0x10ed865e7?, 0x1?, 0x23?, 0xc000070688?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070630 sp=0xc000070610 pc=0x10edb7cae > runtime.runfinq() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:196 +0x107 fp=0xc0000707e0 sp=0xc000070630 pc=0x10ed62a47 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x10edbf7e1 > created by runtime.createfing in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:166 +0x3d > > goroutine 19 gp=0xc000103180 m=nil [chan receive]: > runtime.gopark(0xc0002297c0?, 0xc000010048?, 0x60?, 0xc7?, 0x10ee981c8?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006c718 sp=0xc00006c6f8 pc=0x10edb7cae > runtime.chanrecv(0xc000110310, 0x0, 0x1) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:664 +0x445 fp=0xc00006c790 sp=0xc00006c718 pc=0x10ed54845 > runtime.chanrecv1(0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:506 +0x12 fp=0xc00006c7b8 sp=0xc00006c790 pc=0x10ed543d2 > runtime.unique_runtime_registerUniqueMapCleanup.func2(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1796 > runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1799 +0x2f fp=0xc00006c7e0 sp=0xc00006c7b8 pc=0x10ed66bcf > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x10edbf7e1 > created by unique.runtime_registerUniqueMapCleanup in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1794 +0x79 > > goroutine 20 gp=0xc000103500 m=nil [GC worker (idle)]: > runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006cf38 sp=0xc00006cf18 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006cfc8 sp=0xc00006cf38 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006cfe0 sp=0xc00006cfc8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]: > runtime.gopark(0xbc335d31ca6?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]: > runtime.gopark(0xbc336491363?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000072738 sp=0xc000072718 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc0000727c8 sp=0xc000072738 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc0000727e0 sp=0xc0000727c8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle)]: > runtime.gopark(0xbc335d319e1?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006d738 sp=0xc00006d718 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006d7c8 sp=0xc00006d738 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]: > runtime.gopark(0xbc335d37da0?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]: > runtime.gopark(0xbc335d321c0?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle)]: > runtime.gopark(0xbc33663a71c?, 0x1?, 0xb6?, 0xda?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000072f38 sp=0xc000072f18 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000072fc8 sp=0xc000072f38 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc000072fe0 sp=0xc000072fc8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 7 gp=0xc000003dc0 m=nil [GC worker (idle)]: > runtime.gopark(0xbc336576ba9?, 0x3?, 0xd7?, 0x24?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000073738 sp=0xc000073718 pc=0x10edb7cae > runtime.gcBgMarkWorker(0xc000111730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc0000737c8 sp=0xc000073738 pc=0x10ed65ee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x10ed65dc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x10edbf7e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 8 gp=0xc000504fc0 m=nil [sync.WaitGroup.Wait]: > runtime.gopark(0x0?, 0x0?, 0x20?, 0x21?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00050d6d0 sp=0xc00050d6b0 pc=0x10edb7cae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.semacquire1(0xc0000c2658, 0x0, 0x1, 0x0, 0x18) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:188 +0x21d fp=0xc00050d738 sp=0xc00050d6d0 pc=0x10ed9769d > sync.runtime_SemacquireWaitGroup(0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:110 +0x25 fp=0xc00050d770 sp=0xc00050d738 pc=0x10edb9645 > sync.(*WaitGroup).Wait(0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/waitgroup.go:118 +0x48 fp=0xc00050d798 sp=0xc00050d770 pc=0x10edcb228 > github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0000c25a0, {0x110210420, 0xc0000baf00}) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:366 +0x2a fp=0xc00050d7b8 sp=0xc00050d798 pc=0x10f2a498a > github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x28 fp=0xc00050d7e0 sp=0xc00050d7b8 pc=0x10f2aa9c8 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00050d7e8 sp=0xc00050d7e0 pc=0x10edbf7e1 > created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x4c9 > > goroutine 37 gp=0xc000002000 m=nil [IO wait]: > runtime.gopark(0x5?, 0xc0000ec761?, 0x1?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000507dd8 sp=0xc000507db8 pc=0x10edb7cae > runtime.netpollblock(0x10edd9665?, 0xed520a6?, 0x1?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc000507e10 sp=0xc000507dd8 pc=0x10ed7d497 > internal/poll.runtime_pollWait(0x1576f3f58, 0x72) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc000507e30 sp=0xc000507e10 pc=0x10edb6f05 > internal/poll.(*pollDesc).wait(0xc0000b9080?, 0xc0000ec761?, 0x0) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000507e58 sp=0xc000507e30 pc=0x10ee3c527 > internal/poll.(*pollDesc).waitRead(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89 > internal/poll.(*FD).Read(0xc0000b9080, {0xc0000ec761, 0x1, 0x1}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:165 +0x27a fp=0xc000507ef0 sp=0xc000507e58 pc=0x10ee3d81a > net.(*netFD).Read(0xc0000b9080, {0xc0000ec761?, 0x0?, 0x0?}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_posix.go:55 +0x25 fp=0xc000507f38 sp=0xc000507ef0 pc=0x10eeb3825 > net.(*conn).Read(0xc00011c908, {0xc0000ec761?, 0x0?, 0x0?}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/net.go:194 +0x45 fp=0xc000507f80 sp=0xc000507f38 pc=0x10eec12c5 > net/http.(*connReader).backgroundRead(0xc0000ec750) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:690 +0x37 fp=0xc000507fc8 sp=0xc000507f80 pc=0x10f0aebb7 > net/http.(*connReader).startBackgroundRead.gowrap2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0x25 fp=0xc000507fe0 sp=0xc000507fc8 pc=0x10f0aeae5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000507fe8 sp=0xc000507fe0 pc=0x10edbf7e1 > created by net/http.(*connReader).startBackgroundRead in goroutine 9 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0xb6 > > rax 0x0 > rbx 0x6 > rcx 0x700003d838b8 > rdx 0x0 > rdi 0x1c03 > rsi 0x6 > rbp 0x700003d838e0 > rsp 0x700003d838b8 > r8 0xd4b00000000 > r9 0x160300000003 > r10 0x7ff85b0519c0 > r11 0x246 > r12 0x7b9 > r13 0x157a932a0 > r14 0x1c03 > r15 0x16 > rip 0x7ff819409846 > rflags 0x246 > cs 0x7 > fs 0x0 > gs 0x0 > time=2025-08-25T17:28:15.631+03:00 level=ERROR source=server.go:409 msg="llama runner terminated" error="exit status 2" > time=2025-08-25T17:28:15.631+03:00 level=INFO source=sched.go:441 msg="Load failed" model=/Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 error="do load request: Post \"http://127.0.0.1:57949/load\": EOF" > [GIN] 2025/08/25 - 17:28:15 | 500 | 1.74070275s | 127.0.0.1 | POST "/api/generate" > time=2025-08-25T17:28:38.634+03:00 level=INFO source=server.go:383 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 --port 57971" > time=2025-08-25T17:28:38.640+03:00 level=INFO source=server.go:488 msg="system memory" total="16.0 GiB" free="5.8 GiB" free_swap="0 B" > time=2025-08-25T17:28:38.641+03:00 level=INFO source=server.go:531 msg=offload library=cpu layers.requested=-1 layers.model=27 layers.offload=0 layers.split=[] memory.available="[5.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.3 GiB" memory.required.partial="0 B" memory.required.kv="38.0 MiB" memory.required.allocations="[1.3 GiB]" memory.weights.total="762.5 MiB" memory.weights.repeating="456.5 MiB" memory.weights.nonrepeating="306.0 MiB" memory.graph.full="514.2 MiB" memory.graph.partial="750.5 MiB" > time=2025-08-25T17:28:38.668+03:00 level=INFO source=runner.go:1006 msg="starting ollama engine" > time=2025-08-25T17:28:38.668+03:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:57971" > time=2025-08-25T17:28:38.675+03:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" > time=2025-08-25T17:28:38.762+03:00 level=INFO source=ggml.go:130 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=340 num_key_values=32 > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed > (lldb) process attach --pid 73757 > error: attach failed: attach failed (Not allowed to attach to process. Look in the console messages (Console.app), near the debugserver entries, when the attach failed. The subsystem that denied the attach permission will likely have logged an informative message about why it was denied.) > SIGABRT: abort > PC=0x7ff819409846 m=6 sigcode=0 > signal arrived during cgo execution > > goroutine 7 gp=0xc000584c40 m=6 mp=0xc000180008 [syscall]: > runtime.cgocall(0x10feb8cb0, 0xc000046720) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/cgocall.go:167 +0x4b fp=0xc0000466f8 sp=0xc0000466c0 pc=0x10f1dc88b > github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x6000019f0840) > _cgo_gotypes.go:195 +0x3a fp=0xc000046720 sp=0xc0000466f8 pc=0x10f58945a > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003c094, 0x2b}) > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0000467b8 sp=0xc000046720 pc=0x10f588ef5 > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1() > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x546 fp=0xc000046a18 sp=0xc0000467b8 pc=0x10f588d46 > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046a60 sp=0xc000046a18 pc=0x10f588722 > sync.(*Once).doSlow(0x1106383b0?, 0x110f0b1a0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046ab8 sp=0xc000046a60 pc=0x10f1f1deb > sync.(*Once).Do(0x0?, 0xc000046b60?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046ad8 sp=0xc000046ab8 pc=0x10f1f1d19 > github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046b08 sp=0xc000046ad8 pc=0x10f58868d > github.com/ollama/ollama/ml/backend/ggml.init.func1() > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:44 +0x23 fp=0xc000046b98 sp=0xc000046b08 pc=0x10f608803 > github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:27 +0x62 fp=0xc000046be0 sp=0xc000046b98 pc=0x10f608702 > sync.(*Once).doSlow(0x100011062e0e8?, 0xc000074618?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:78 +0xab fp=0xc000046c38 sp=0xc000046be0 pc=0x10f1f1deb > sync.(*Once).Do(0x10f1f1ea0?, 0x110f0b79c?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/once.go:69 +0x19 fp=0xc000046c58 sp=0xc000046c38 pc=0x10f1f1d19 > github.com/ollama/ollama/ml/backend/ggml.init.OnceFunc.func3() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/oncefunc.go:32 +0x2d fp=0xc000046c88 sp=0xc000046c58 pc=0x10f60866d > github.com/ollama/ollama/ml/backend/ggml.New({0x7ff7b0d97ae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}) > /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:141 +0x124 fp=0xc000047558 sp=0xc000046c88 pc=0x10f6106e4 > github.com/ollama/ollama/ml.NewBackend({0x7ff7b0d97ae2, 0x6c}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}) > /Users/runner/work/ollama/ollama/ml/backend.go:358 +0x9c fp=0xc0000475a8 sp=0xc000047558 pc=0x10f5b021c > github.com/ollama/ollama/model.New({0x7ff7b0d97ae2?, 0x0?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}) > /Users/runner/work/ollama/ollama/model/model.go:102 +0x7e fp=0xc0000476a0 sp=0xc0000475a8 pc=0x10f62353e > github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc0002a8d20, {0x7ff7b0d97ae2?, 0x10f4d3b1a?}, {0x1, 0x4, {0x0, 0x0, 0x0}, 0x0}, {0x0, ...}, ...) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:854 +0xcc fp=0xc000047730 sp=0xc0000476a0 pc=0x10f6d0a0c > github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc0002a8d20, {0x110636148, 0xc00024ab60}, 0xc0000e6f00) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:952 +0x54d fp=0xc000047ac0 sp=0xc000047730 pc=0x10f6d158d > github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x110636148?, 0xc00024ab60?}, 0xc000115b40?) > <autogenerated>:1 +0x36 fp=0xc000047af0 sp=0xc000047ac0 pc=0x10f6d2d96 > net/http.HandlerFunc.ServeHTTP(0xc0000e4300?, {0x110636148?, 0xc00024ab60?}, 0xc000115b60?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2294 +0x29 fp=0xc000047b18 sp=0xc000047af0 pc=0x10f4de7e9 > net/http.(*ServeMux).ServeHTTP(0x10f1853c5?, {0x110636148, 0xc00024ab60}, 0xc0000e6f00) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2822 +0x1c4 fp=0xc000047b68 sp=0xc000047b18 pc=0x10f4e06e4 > net/http.serverHandler.ServeHTTP({0x1106327b0?}, {0x110636148?, 0xc00024ab60?}, 0x1?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3301 +0x8e fp=0xc000047b98 sp=0xc000047b68 pc=0x10f4fe16e > net/http.(*conn).serve(0xc0000f43f0, {0x1106383e8, 0xc0000f8660}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:2102 +0x625 fp=0xc000047fb8 sp=0xc000047b98 pc=0x10f4dcce5 > net/http.(*Server).Serve.gowrap3() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x28 fp=0xc000047fe0 sp=0xc000047fb8 pc=0x10f4e25a8 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000047fe8 sp=0xc000047fe0 pc=0x10f1e77e1 > created by net/http.(*Server).Serve in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3454 +0x485 > > goroutine 1 gp=0xc000002380 m=nil [IO wait]: > runtime.gopark(0xc0005957e0?, 0x10f202918?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc001585790 sp=0xc001585770 pc=0x10f1dfcae > runtime.netpollblock(0xc0005957e0?, 0xf17a0a6?, 0x1?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0015857c8 sp=0xc001585790 pc=0x10f1a5497 > internal/poll.runtime_pollWait(0x157cfb830, 0x72) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc0015857e8 sp=0xc0015857c8 pc=0x10f1def05 > internal/poll.(*pollDesc).wait(0xc000633100?, 0x9000f86c0?, 0x0) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc001585810 sp=0xc0015857e8 pc=0x10f264527 > internal/poll.(*pollDesc).waitRead(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89 > internal/poll.(*FD).Accept(0xc000633100) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:620 +0x295 fp=0xc0015858b8 sp=0xc001585810 pc=0x10f2698f5 > net.(*netFD).accept(0xc000633100) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_unix.go:172 +0x29 fp=0xc001585970 sp=0xc0015858b8 pc=0x10f2dd7c9 > net.(*TCPListener).accept(0xc00004ee00) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock_posix.go:159 +0x1b fp=0xc0015859c0 sp=0xc001585970 pc=0x10f2f245b > net.(*TCPListener).Accept(0xc00004ee00) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/tcpsock.go:380 +0x30 fp=0xc0015859f0 sp=0xc0015859c0 pc=0x10f2f1350 > net/http.(*onceCloseListener).Accept(0xc0000f43f0?) > <autogenerated>:1 +0x24 fp=0xc001585a08 sp=0xc0015859f0 pc=0x10f50a8e4 > net/http.(*Server).Serve(0xc000277600, {0x110635f68, 0xc00004ee00}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:3424 +0x30c fp=0xc001585b38 sp=0xc001585a08 pc=0x10f4e21ac > github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0001b8030, 0x4, 0x4}) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1044 +0x8c6 fp=0xc001585d08 sp=0xc001585b38 pc=0x10f6d2766 > github.com/ollama/ollama/runner.Execute({0xc0001b8010?, 0x0?, 0x0?}) > /Users/runner/work/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc001585d30 sp=0xc001585d08 pc=0x10f6d2fa9 > github.com/ollama/ollama/cmd.NewCLI.func2(0xc000277400?, {0x1101a6098?, 0x4?, 0x1101a609c?}) > /Users/runner/work/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc001585d58 sp=0xc001585d30 pc=0x10fe38525 > github.com/spf13/cobra.(*Command).execute(0xc0000fcf08, {0xc0000bcb90, 0x5, 0x5}) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc001585e78 sp=0xc001585d58 pc=0x10f355f1c > github.com/spf13/cobra.(*Command).ExecuteC(0xc000642908) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc001585f30 sp=0xc001585e78 pc=0x10f356765 > github.com/spf13/cobra.(*Command).Execute(...) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992 > github.com/spf13/cobra.(*Command).ExecuteContext(...) > /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 > main.main() > /Users/runner/work/ollama/ollama/main.go:12 +0x4d fp=0xc001585f50 sp=0xc001585f30 pc=0x10fe3900d > runtime.main() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:283 +0x28b fp=0xc001585fe0 sp=0xc001585f50 pc=0x10f1ac1cb > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc001585fe8 sp=0xc001585fe0 pc=0x10f1e77e1 > > goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: > runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070fa8 sp=0xc000070f88 pc=0x10f1dfcae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.forcegchelper() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:348 +0xb3 fp=0xc000070fe0 sp=0xc000070fa8 pc=0x10f1ac513 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x10f1e77e1 > created by runtime.init.7 in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:336 +0x1a > > goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: > runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071780 sp=0xc000071760 pc=0x10f1dfcae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.bgsweep(0xc00009c000) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcsweep.go:316 +0xdf fp=0xc0000717c8 sp=0xc000071780 pc=0x10f19763f > runtime.gcenable.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x25 fp=0xc0000717e0 sp=0xc0000717c8 pc=0x10f18ba85 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000717e8 sp=0xc0000717e0 pc=0x10f1e77e1 > created by runtime.gcenable in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:204 +0x66 > > goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: > runtime.gopark(0x10000?, 0x1103636a8?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000071f78 sp=0xc000071f58 pc=0x10f1dfcae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.(*scavengerState).park(0x110ee1ee0) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:425 +0x49 fp=0xc000071fa8 sp=0xc000071f78 pc=0x10f195069 > runtime.bgscavenge(0xc00009c000) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgcscavenge.go:658 +0x59 fp=0xc000071fc8 sp=0xc000071fa8 pc=0x10f1955f9 > runtime.gcenable.gowrap2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x10f18ba25 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x10f1e77e1 > created by runtime.gcenable in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:205 +0xa5 > > goroutine 18 gp=0xc000182700 m=nil [finalizer wait]: > runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000070688?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000070630 sp=0xc000070610 pc=0x10f1dfcae > runtime.runfinq() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:196 +0x107 fp=0xc0000707e0 sp=0xc000070630 pc=0x10f18aa47 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x10f1e77e1 > created by runtime.createfing in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mfinal.go:166 +0x3d > > goroutine 19 gp=0xc000183180 m=nil [chan receive]: > runtime.gopark(0xc0002c50e0?, 0xc000010060?, 0x60?, 0xc7?, 0x10f2c01c8?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006c718 sp=0xc00006c6f8 pc=0x10f1dfcae > runtime.chanrecv(0xc000192310, 0x0, 0x1) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:664 +0x445 fp=0xc00006c790 sp=0xc00006c718 pc=0x10f17c845 > runtime.chanrecv1(0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/chan.go:506 +0x12 fp=0xc00006c7b8 sp=0xc00006c790 pc=0x10f17c3d2 > runtime.unique_runtime_registerUniqueMapCleanup.func2(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1796 > runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1799 +0x2f fp=0xc00006c7e0 sp=0xc00006c7b8 pc=0x10f18ebcf > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x10f1e77e1 > created by unique.runtime_registerUniqueMapCleanup in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1794 +0x79 > > goroutine 20 gp=0xc0001836c0 m=nil [GC worker (idle)]: > runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006cf38 sp=0xc00006cf18 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006cfc8 sp=0xc00006cf38 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006cfe0 sp=0xc00006cfc8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 21 gp=0xc000183880 m=nil [GC worker (idle)]: > runtime.gopark(0xbc8d995c01e?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006d738 sp=0xc00006d718 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006d7c8 sp=0xc00006d738 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 34 gp=0xc000584000 m=nil [GC worker (idle)]: > runtime.gopark(0xbc8d995c452?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058a738 sp=0xc00058a718 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00058a7c8 sp=0xc00058a738 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00058a7e0 sp=0xc00058a7c8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058a7e8 sp=0xc00058a7e0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 35 gp=0xc0005841c0 m=nil [GC worker (idle)]: > runtime.gopark(0xbc8d995e30f?, 0x0?, 0x0?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058af38 sp=0xc00058af18 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00058afc8 sp=0xc00058af38 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00058afe0 sp=0xc00058afc8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058afe8 sp=0xc00058afe0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]: > runtime.gopark(0xbc8d995c8c9?, 0x1?, 0xfa?, 0x7c?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc000072738 sp=0xc000072718 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc0000727c8 sp=0xc000072738 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc0000727e0 sp=0xc0000727c8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 22 gp=0xc000183a40 m=nil [GC worker (idle)]: > runtime.gopark(0xbc8d995bfdd?, 0x3?, 0xd?, 0xdc?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006df38 sp=0xc00006df18 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006dfc8 sp=0xc00006df38 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 23 gp=0xc000183c00 m=nil [GC worker (idle)]: > runtime.gopark(0xbc8d995c0db?, 0x1?, 0xe9?, 0x1b?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 36 gp=0xc000584380 m=nil [GC worker (idle)]: > runtime.gopark(0xbc8da2ecdfa?, 0x1?, 0x9b?, 0x1a?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058b738 sp=0xc00058b718 pc=0x10f1dfcae > runtime.gcBgMarkWorker(0xc000193730) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00058b7c8 sp=0xc00058b738 pc=0x10f18dee9 > runtime.gcBgMarkStartWorkers.gowrap1() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x25 fp=0xc00058b7e0 sp=0xc00058b7c8 pc=0x10f18ddc5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058b7e8 sp=0xc00058b7e0 pc=0x10f1e77e1 > created by runtime.gcBgMarkStartWorkers in goroutine 1 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/mgc.go:1339 +0x105 > > goroutine 6 gp=0xc000584a80 m=nil [sync.WaitGroup.Wait]: > runtime.gopark(0x0?, 0x0?, 0x80?, 0x1?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058d6d0 sp=0xc00058d6b0 pc=0x10f1dfcae > runtime.goparkunlock(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:441 > runtime.semacquire1(0xc0002a8dd8, 0x0, 0x1, 0x0, 0x18) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:188 +0x21d fp=0xc00058d738 sp=0xc00058d6d0 pc=0x10f1bf69d > sync.runtime_SemacquireWaitGroup(0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/sema.go:110 +0x25 fp=0xc00058d770 sp=0xc00058d738 pc=0x10f1e1645 > sync.(*WaitGroup).Wait(0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/sync/waitgroup.go:118 +0x48 fp=0xc00058d798 sp=0xc00058d770 pc=0x10f1f3228 > github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002a8d20, {0x110638420, 0xc0000bcc30}) > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:366 +0x2a fp=0xc00058d7b8 sp=0xc00058d798 pc=0x10f6cc98a > github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x28 fp=0xc00058d7e0 sp=0xc00058d7b8 pc=0x10f6d29c8 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058d7e8 sp=0xc00058d7e0 pc=0x10f1e77e1 > created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 > /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1019 +0x4c9 > > goroutine 9 gp=0xc000584e00 m=nil [IO wait]: > runtime.gopark(0x5?, 0xc0000f8761?, 0x1?, 0x0?, 0x0?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/proc.go:435 +0xce fp=0xc00058ddd8 sp=0xc00058ddb8 pc=0x10f1dfcae > runtime.netpollblock(0x10f201665?, 0xf17a0a6?, 0x1?) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:575 +0xf7 fp=0xc00058de10 sp=0xc00058ddd8 pc=0x10f1a5497 > internal/poll.runtime_pollWait(0x157cfb718, 0x72) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/netpoll.go:351 +0x85 fp=0xc00058de30 sp=0xc00058de10 pc=0x10f1def05 > internal/poll.(*pollDesc).wait(0xc000633180?, 0xc0000f8761?, 0x0) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00058de58 sp=0xc00058de30 pc=0x10f264527 > internal/poll.(*pollDesc).waitRead(...) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_poll_runtime.go:89 > internal/poll.(*FD).Read(0xc000633180, {0xc0000f8761, 0x1, 0x1}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/internal/poll/fd_unix.go:165 +0x27a fp=0xc00058def0 sp=0xc00058de58 pc=0x10f26581a > net.(*netFD).Read(0xc000633180, {0xc0000f8761?, 0xc00004eed8?, 0xc00058df70?}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/fd_posix.go:55 +0x25 fp=0xc00058df38 sp=0xc00058def0 pc=0x10f2db825 > net.(*conn).Read(0xc000074598, {0xc0000f8761?, 0x0?, 0x0?}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/net.go:194 +0x45 fp=0xc00058df80 sp=0xc00058df38 pc=0x10f2e92c5 > net/http.(*connReader).backgroundRead(0xc0000f8750) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:690 +0x37 fp=0xc00058dfc8 sp=0xc00058df80 pc=0x10f4d6bb7 > net/http.(*connReader).startBackgroundRead.gowrap2() > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0x25 fp=0xc00058dfe0 sp=0xc00058dfc8 pc=0x10f4d6ae5 > runtime.goexit({}) > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00058dfe8 sp=0xc00058dfe0 pc=0x10f1e77e1 > created by net/http.(*connReader).startBackgroundRead in goroutine 7 > /Users/runner/hostedtoolcache/go/1.24.0/arm64/src/net/http/server.go:686 +0xb6 > > rax 0x0 > rbx 0x6 > rcx 0x7000032718b8 > rdx 0x0 > rdi 0x1b03 > rsi 0x6 > rbp 0x7000032718e0 > rsp 0x7000032718b8 > r8 0xd4b00000000 > r9 0x180300000003 > r10 0x7ff85b0519c0 > r11 0x246 > r12 0x7b9 > r13 0x157ebb2a0 > r14 0x1b03 > r15 0x16 > rip 0x7ff819409846 > rflags 0x246 > cs 0x7 > fs 0x0 > gs 0x0 > time=2025-08-25T17:28:39.242+03:00 level=ERROR source=server.go:409 msg="llama runner terminated" error="exit status 2" > time=2025-08-25T17:28:39.242+03:00 level=INFO source=sched.go:441 msg="Load failed" model=/Users/nire0510/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 error="do load request: Post \"http://127.0.0.1:57971/load\": EOF" > [GIN] 2025/08/25 - 17:28:39 | 500 | 1.014162474s | 127.0.0.1 | POST "/api/generate" > ` _Originally posted by @nire0510 in [#12025](https://github.com/ollama/ollama/issues/12025#issuecomment-3220614858)_

GiteaMirror added the bug macos labels 2026-04-12 20:14:38 -05:00

GiteaMirror closed this issue

2026-04-12 20:14:40 -05:00

GiteaMirror commented

2026-04-12 20:14:41 -05:00

@rick-github commented on GitHub (Aug 25, 2025):

@ippocode @HilaryTraut @nire0510

@rick-github commented on GitHub (Aug 25, 2025): @ippocode @HilaryTraut @nire0510

GiteaMirror commented

2026-04-12 20:14:42 -05:00

@rick-github commented on GitHub (Aug 25, 2025):

ippocode, HilaryTraut and nire0510 are on MacOS and the runner is asserting on ggml_uncaught_exception with models gemma3:270m-it-q8_0, gpt-oss:20b and gemma3:1b-it-q4_K_M respectively.

@rick-github commented on GitHub (Aug 25, 2025): ippocode, HilaryTraut and nire0510 are on MacOS and the runner is asserting on ggml_uncaught_exception with models gemma3:270m-it-q8_0, gpt-oss:20b and gemma3:1b-it-q4_K_M respectively.

GiteaMirror commented

2026-04-12 20:14:43 -05:00

@rick-github commented on GitHub (Aug 25, 2025):

@nire0510 Can you confirm that you are also on 0.11.6?

@rick-github commented on GitHub (Aug 25, 2025): @nire0510 Can you confirm that you are also on 0.11.6?

GiteaMirror commented

2026-04-12 20:14:44 -05:00

@nire0510 commented on GitHub (Aug 25, 2025):

@nire0510 Can you confirm that you are also on 0.11.6?

affirmative @rick-github

@nire0510 commented on GitHub (Aug 25, 2025): > [@nire0510](https://github.com/nire0510) Can you confirm that you are also on 0.11.6? affirmative @rick-github

GiteaMirror commented

2026-04-12 20:14:44 -05:00

@pdevine commented on GitHub (Aug 25, 2025):

cc @dhiltgen

@pdevine commented on GitHub (Aug 25, 2025): cc @dhiltgen

GiteaMirror commented

2026-04-12 20:14:45 -05:00

@rick-github commented on GitHub (Aug 26, 2025):

HilaryTraut: Mac OS 15.6 Intel

@ippocode @nire0510 could you add the version of MacOS you are using?

@rick-github commented on GitHub (Aug 26, 2025): HilaryTraut: Mac OS 15.6 Intel @ippocode @nire0510 could you add the version of MacOS you are using?

GiteaMirror commented

2026-04-12 20:14:46 -05:00

@pdevine commented on GitHub (Aug 26, 2025):

It seems like this is macOS on Intel?

@pdevine commented on GitHub (Aug 26, 2025): It seems like this is macOS on Intel?

GiteaMirror commented

2026-04-12 20:14:47 -05:00

@rick-github commented on GitHub (Aug 26, 2025):

Correct in the case of HilaryTraut.

@rick-github commented on GitHub (Aug 26, 2025): Correct in the case of HilaryTraut.

GiteaMirror commented

2026-04-12 20:14:48 -05:00

@nire0510 commented on GitHub (Aug 26, 2025):

HilaryTraut: Mac OS 15.6 Intel

@ippocode @nire0510 could you add the version of MacOS you are using?

macOS 15.6.1 (24G90) (Intel)

@nire0510 commented on GitHub (Aug 26, 2025): > HilaryTraut: Mac OS 15.6 Intel > > [@ippocode](https://github.com/ippocode) [@nire0510](https://github.com/nire0510) could you add the version of MacOS you are using? macOS 15.6.1 (24G90) (Intel)

GiteaMirror commented

2026-04-12 20:14:50 -05:00

@czj942650673 commented on GitHub (Aug 27, 2025):

time=2025-08-27T13:41:47.882+08:00 level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\94265\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-08-27T13:41:47.893+08:00 level=INFO source=images.go:477 msg="total blobs: 17"
time=2025-08-27T13:41:47.902+08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 12"
time=2025-08-27T13:41:47.902+08:00 level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.7)"
time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=24 efficiency=16 threads=24
time=2025-08-27T13:41:48.047+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5080 Laptop GPU" total="15.9 GiB" available="14.6 GiB"
time=2025-08-27T13:41:48.047+08:00 level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB"
[GIN] 2025/08/27 - 13:41:48 | 200 | 0s | 127.0.0.1 | GET "/"
[GIN] 2025/08/27 - 13:41:48 | 200 | 516.2µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/08/27 - 13:41:48 | 404 | 1.5035ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:41:49 | 404 | 1.0593ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:41:51 | 404 | 518.5µs | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:42:01 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/08/27 - 13:42:01 | 200 | 52.1507ms | 127.0.0.1 | POST "/api/show"
time=2025-08-27T13:42:02.092+08:00 level=INFO source=server.go:383 msg="starting runner" cmd="C:\Users\94265\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --model C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 --port 51784"
time=2025-08-27T13:42:02.109+08:00 level=INFO source=server.go:488 msg="system memory" total="31.4 GiB" free="16.8 GiB" free_swap="19.4 GiB"
time=2025-08-27T13:42:02.112+08:00 level=INFO source=server.go:528 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=36 layers.split=[36] memory.available="[7.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.5 GiB" memory.required.partial="6.1 GiB" memory.required.kv="144.0 MiB" memory.required.allocations="[6.1 GiB]" memory.weights.total="5.7 GiB" memory.weights.repeating="5.2 GiB" memory.weights.nonrepeating="593.5 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" projector.weights="1.2 GiB" projector.graph="1.6 GiB"
time=2025-08-27T13:42:02.130+08:00 level=INFO source=runner.go:1006 msg="starting ollama engine"
time=2025-08-27T13:42:02.134+08:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:51784"
time=2025-08-27T13:42:02.145+08:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:36[ID:GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 Layers:36(0..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-08-27T13:42:02.160+08:00 level=INFO source=ggml.go:130 msg="" architecture=qwen25vl file_type=F16 name="" description="" num_tensors=953 num_key_values=36
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 5080 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-a5d2d457-1c84-896e-3d55-359d99f0b824
load_backend: loaded CUDA backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll
load_backend: loaded CPU backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2025-08-27T13:42:02.273+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-08-27T13:42:02.515+08:00 level=INFO source=ggml.go:486 msg="offloading 36 repeating layers to GPU"
time=2025-08-27T13:42:02.515+08:00 level=INFO source=ggml.go:490 msg="offloading output layer to CPU"
time=2025-08-27T13:42:02.515+08:00 level=INFO source=ggml.go:497 msg="offloaded 36/37 layers to GPU"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="5.2 GiB"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="2.4 GiB"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="144.0 MiB"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="364.0 MiB"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="1.6 GiB"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:342 msg="total memory" size="9.6 GiB"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=sched.go:473 msg="loaded runners" count=1
time=2025-08-27T13:42:02.516+08:00 level=INFO source=server.go:1231 msg="waiting for llama runner to start responding"
time=2025-08-27T13:42:02.516+08:00 level=INFO source=server.go:1265 msg="waiting for server to become available" status="llm server loading model"
time=2025-08-27T13:42:03.768+08:00 level=INFO source=server.go:1269 msg="llama runner started in 1.68 seconds"
[GIN] 2025/08/27 - 13:42:03 | 200 | 1.8563295s | 127.0.0.1 | POST "/api/generate"
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
time=2025-08-27T13:42:07.115+08:00 level=ERROR source=server.go:1439 msg="post predict" error="Post "http://127.0.0.1:51784/completion": read tcp 127.0.0.1:51788->127.0.0.1:51784: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/08/27 - 13:42:07 | 200 | 483.6896ms | 127.0.0.1 | POST "/api/chat"
time=2025-08-27T13:47:12.130+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0134031 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=34256 runner.model=C:\Users\94265.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119
time=2025-08-27T13:47:12.380+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2632392 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=34256 runner.model=C:\Users\94265.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119
time=2025-08-27T13:47:12.630+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5130482 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=34256 runner.model=C:\Users\94265.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119
[GIN] 2025/08/27 - 13:55:12 | 404 | 0s | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:55:12 | 200 | 1.0541ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/08/27 - 13:55:13 | 404 | 0s | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:55:15 | 404 | 591.7µs | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:55:17 | 200 | 28.2288ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:55:28 | 200 | 511.7µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/08/27 - 13:55:28 | 200 | 28.2741ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/27 - 13:55:28 | 200 | 24.549ms | 127.0.0.1 | POST "/api/show"
time=2025-08-27T13:55:28.304+08:00 level=INFO source=server.go:383 msg="starting runner" cmd="C:\Users\94265\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --model C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 --port 53165"
time=2025-08-27T13:55:28.316+08:00 level=INFO source=server.go:488 msg="system memory" total="31.4 GiB" free="15.4 GiB" free_swap="19.6 GiB"
time=2025-08-27T13:55:28.317+08:00 level=INFO source=server.go:528 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=36 layers.split=[36] memory.available="[7.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.5 GiB" memory.required.partial="6.1 GiB" memory.required.kv="144.0 MiB" memory.required.allocations="[6.1 GiB]" memory.weights.total="5.7 GiB" memory.weights.repeating="5.2 GiB" memory.weights.nonrepeating="593.5 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" projector.weights="1.2 GiB" projector.graph="1.6 GiB"
time=2025-08-27T13:55:28.344+08:00 level=INFO source=runner.go:1006 msg="starting ollama engine"
time=2025-08-27T13:55:28.349+08:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:53165"
time=2025-08-27T13:55:28.350+08:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:36[ID:GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 Layers:36(0..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-08-27T13:55:28.365+08:00 level=INFO source=ggml.go:130 msg="" architecture=qwen25vl file_type=F16 name="" description="" num_tensors=953 num_key_values=36
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 5080 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-a5d2d457-1c84-896e-3d55-359d99f0b824
load_backend: loaded CUDA backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll
load_backend: loaded CPU backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2025-08-27T13:55:28.481+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-08-27T13:55:28.745+08:00 level=INFO source=ggml.go:486 msg="offloading 36 repeating layers to GPU"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=ggml.go:490 msg="offloading output layer to CPU"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=ggml.go:497 msg="offloaded 36/37 layers to GPU"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="5.2 GiB"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="2.4 GiB"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="144.0 MiB"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="364.0 MiB"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="1.6 GiB"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:342 msg="total memory" size="9.6 GiB"
time=2025-08-27T13:55:28.745+08:00 level=INFO source=sched.go:473 msg="loaded runners" count=1
time=2025-08-27T13:55:28.745+08:00 level=INFO source=server.go:1231 msg="waiting for llama runner to start responding"
time=2025-08-27T13:55:28.746+08:00 level=INFO source=server.go:1265 msg="waiting for server to become available" status="llm server loading model"
time=2025-08-27T13:55:29.997+08:00 level=INFO source=server.go:1269 msg="llama runner started in 1.69 seconds"
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
time=2025-08-27T13:55:30.212+08:00 level=ERROR source=server.go:1439 msg="post predict" error="Post "http://127.0.0.1:53165/completion": read tcp 127.0.0.1:53169->127.0.0.1:53165: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/08/27 - 13:55:30 | 200 | 2.0287446s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/08/27 - 13:56:00 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/08/27 - 13:56:00 | 200 | 0s | 127.0.0.1 | GET "/api/ps"
[GIN] 2025/08/27 - 13:58:39 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/08/27 - 13:58:39 | 200 | 0s | 127.0.0.1 | GET "/api/ps"
[GIN] 2025/08/27 - 13:58:44 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/08/27 - 13:58:44 | 200 | 27.4905ms | 127.0.0.1 | POST "/api/show"
time=2025-08-27T13:58:49.294+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0179735 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=11528 runner.model=C:\Users\94265.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119
time=2025-08-27T13:58:49.388+08:00 level=INFO source=server.go:383 msg="starting runner" cmd="C:\Users\94265\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --model C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 --port 53284"
time=2025-08-27T13:58:49.401+08:00 level=INFO source=server.go:488 msg="system memory" total="31.4 GiB" free="15.5 GiB" free_swap="19.3 GiB"
time=2025-08-27T13:58:49.402+08:00 level=INFO source=server.go:528 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=36 layers.split=[36] memory.available="[7.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.5 GiB" memory.required.partial="6.1 GiB" memory.required.kv="144.0 MiB" memory.required.allocations="[6.1 GiB]" memory.weights.total="5.7 GiB" memory.weights.repeating="5.2 GiB" memory.weights.nonrepeating="593.5 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" projector.weights="1.2 GiB" projector.graph="1.6 GiB"
time=2025-08-27T13:58:49.426+08:00 level=INFO source=runner.go:1006 msg="starting ollama engine"
time=2025-08-27T13:58:49.430+08:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:53284"
time=2025-08-27T13:58:49.434+08:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:36[ID:GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 Layers:36(0..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-08-27T13:58:49.450+08:00 level=INFO source=ggml.go:130 msg="" architecture=qwen25vl file_type=F16 name="" description="" num_tensors=953 num_key_values=36
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 5080 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-a5d2d457-1c84-896e-3d55-359d99f0b824
load_backend: loaded CUDA backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll
time=2025-08-27T13:58:49.544+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2681944 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=11528 runner.model=C:\Users\94265.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119
load_backend: loaded CPU backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2025-08-27T13:58:49.551+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-08-27T13:58:49.790+08:00 level=INFO source=ggml.go:486 msg="offloading 36 repeating layers to GPU"
time=2025-08-27T13:58:49.790+08:00 level=INFO source=ggml.go:490 msg="offloading output layer to CPU"
time=2025-08-27T13:58:49.790+08:00 level=INFO source=ggml.go:497 msg="offloaded 36/37 layers to GPU"
time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="5.2 GiB"
time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="2.4 GiB"
time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="144.0 MiB"
time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="364.0 MiB"
time=2025-08-27T13:58:49.791+08:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="1.6 GiB"
time=2025-08-27T13:58:49.791+08:00 level=INFO source=backend.go:342 msg="total memory" size="9.6 GiB"
time=2025-08-27T13:58:49.791+08:00 level=INFO source=sched.go:473 msg="loaded runners" count=1
time=2025-08-27T13:58:49.791+08:00 level=INFO source=server.go:1231 msg="waiting for llama runner to start responding"
time=2025-08-27T13:58:49.791+08:00 level=INFO source=server.go:1265 msg="waiting for server to become available" status="llm server loading model"
time=2025-08-27T13:58:51.043+08:00 level=INFO source=server.go:1269 msg="llama runner started in 1.65 seconds"
[GIN] 2025/08/27 - 13:58:51 | 200 | 6.7997025s | 127.0.0.1 | POST "/api/generate"
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error
time=2025-08-27T13:58:53.305+08:00 level=ERROR source=server.go:1439 msg="post predict" error="Post "http://127.0.0.1:53284/completion": read tcp 127.0.0.1:53288->127.0.0.1:53284: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/08/27 - 13:58:53 | 200 | 243.7775ms | 127.0.0.1 | POST "/api/chat"

BUG，after i update ollama to 0.11.7 。 this problem happened。what should i do？

@czj942650673 commented on GitHub (Aug 27, 2025): time=2025-08-27T13:41:47.882+08:00 level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\94265\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-08-27T13:41:47.893+08:00 level=INFO source=images.go:477 msg="total blobs: 17" time=2025-08-27T13:41:47.902+08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 12" time=2025-08-27T13:41:47.902+08:00 level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.7)" time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-08-27T13:41:47.902+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=24 efficiency=16 threads=24 time=2025-08-27T13:41:48.047+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5080 Laptop GPU" total="15.9 GiB" available="14.6 GiB" time=2025-08-27T13:41:48.047+08:00 level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="15.9 GiB" threshold="20.0 GiB" [GIN] 2025/08/27 - 13:41:48 | 200 | 0s | 127.0.0.1 | GET "/" [GIN] 2025/08/27 - 13:41:48 | 200 | 516.2µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/27 - 13:41:48 | 404 | 1.5035ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:41:49 | 404 | 1.0593ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:41:51 | 404 | 518.5µs | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:42:01 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/08/27 - 13:42:01 | 200 | 52.1507ms | 127.0.0.1 | POST "/api/show" time=2025-08-27T13:42:02.092+08:00 level=INFO source=server.go:383 msg="starting runner" cmd="C:\\Users\\94265\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\94265\\.ollama\\models\\blobs\\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 --port 51784" time=2025-08-27T13:42:02.109+08:00 level=INFO source=server.go:488 msg="system memory" total="31.4 GiB" free="16.8 GiB" free_swap="19.4 GiB" time=2025-08-27T13:42:02.112+08:00 level=INFO source=server.go:528 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=36 layers.split=[36] memory.available="[7.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.5 GiB" memory.required.partial="6.1 GiB" memory.required.kv="144.0 MiB" memory.required.allocations="[6.1 GiB]" memory.weights.total="5.7 GiB" memory.weights.repeating="5.2 GiB" memory.weights.nonrepeating="593.5 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" projector.weights="1.2 GiB" projector.graph="1.6 GiB" time=2025-08-27T13:42:02.130+08:00 level=INFO source=runner.go:1006 msg="starting ollama engine" time=2025-08-27T13:42:02.134+08:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:51784" time=2025-08-27T13:42:02.145+08:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:36[ID:GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 Layers:36(0..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-08-27T13:42:02.160+08:00 level=INFO source=ggml.go:130 msg="" architecture=qwen25vl file_type=F16 name="" description="" num_tensors=953 num_key_values=36 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 5080 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 load_backend: loaded CUDA backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll load_backend: loaded CPU backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2025-08-27T13:42:02.273+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-08-27T13:42:02.515+08:00 level=INFO source=ggml.go:486 msg="offloading 36 repeating layers to GPU" time=2025-08-27T13:42:02.515+08:00 level=INFO source=ggml.go:490 msg="offloading output layer to CPU" time=2025-08-27T13:42:02.515+08:00 level=INFO source=ggml.go:497 msg="offloaded 36/37 layers to GPU" time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="5.2 GiB" time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="2.4 GiB" time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="144.0 MiB" time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="364.0 MiB" time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="1.6 GiB" time=2025-08-27T13:42:02.516+08:00 level=INFO source=backend.go:342 msg="total memory" size="9.6 GiB" time=2025-08-27T13:42:02.516+08:00 level=INFO source=sched.go:473 msg="loaded runners" count=1 time=2025-08-27T13:42:02.516+08:00 level=INFO source=server.go:1231 msg="waiting for llama runner to start responding" time=2025-08-27T13:42:02.516+08:00 level=INFO source=server.go:1265 msg="waiting for server to become available" status="llm server loading model" time=2025-08-27T13:42:03.768+08:00 level=INFO source=server.go:1269 msg="llama runner started in 1.68 seconds" [GIN] 2025/08/27 - 13:42:03 | 200 | 1.8563295s | 127.0.0.1 | POST "/api/generate" C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error time=2025-08-27T13:42:07.115+08:00 level=ERROR source=server.go:1439 msg="post predict" error="Post \"http://127.0.0.1:51784/completion\": read tcp 127.0.0.1:51788->127.0.0.1:51784: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/08/27 - 13:42:07 | 200 | 483.6896ms | 127.0.0.1 | POST "/api/chat" time=2025-08-27T13:47:12.130+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0134031 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=34256 runner.model=C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 time=2025-08-27T13:47:12.380+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2632392 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=34256 runner.model=C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 time=2025-08-27T13:47:12.630+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5130482 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=34256 runner.model=C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 [GIN] 2025/08/27 - 13:55:12 | 404 | 0s | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:55:12 | 200 | 1.0541ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/27 - 13:55:13 | 404 | 0s | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:55:15 | 404 | 591.7µs | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:55:17 | 200 | 28.2288ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:55:28 | 200 | 511.7µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/27 - 13:55:28 | 200 | 28.2741ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/27 - 13:55:28 | 200 | 24.549ms | 127.0.0.1 | POST "/api/show" time=2025-08-27T13:55:28.304+08:00 level=INFO source=server.go:383 msg="starting runner" cmd="C:\\Users\\94265\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\94265\\.ollama\\models\\blobs\\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 --port 53165" time=2025-08-27T13:55:28.316+08:00 level=INFO source=server.go:488 msg="system memory" total="31.4 GiB" free="15.4 GiB" free_swap="19.6 GiB" time=2025-08-27T13:55:28.317+08:00 level=INFO source=server.go:528 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=36 layers.split=[36] memory.available="[7.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.5 GiB" memory.required.partial="6.1 GiB" memory.required.kv="144.0 MiB" memory.required.allocations="[6.1 GiB]" memory.weights.total="5.7 GiB" memory.weights.repeating="5.2 GiB" memory.weights.nonrepeating="593.5 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" projector.weights="1.2 GiB" projector.graph="1.6 GiB" time=2025-08-27T13:55:28.344+08:00 level=INFO source=runner.go:1006 msg="starting ollama engine" time=2025-08-27T13:55:28.349+08:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:53165" time=2025-08-27T13:55:28.350+08:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:36[ID:GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 Layers:36(0..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-08-27T13:55:28.365+08:00 level=INFO source=ggml.go:130 msg="" architecture=qwen25vl file_type=F16 name="" description="" num_tensors=953 num_key_values=36 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 5080 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 load_backend: loaded CUDA backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll load_backend: loaded CPU backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2025-08-27T13:55:28.481+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-08-27T13:55:28.745+08:00 level=INFO source=ggml.go:486 msg="offloading 36 repeating layers to GPU" time=2025-08-27T13:55:28.745+08:00 level=INFO source=ggml.go:490 msg="offloading output layer to CPU" time=2025-08-27T13:55:28.745+08:00 level=INFO source=ggml.go:497 msg="offloaded 36/37 layers to GPU" time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="5.2 GiB" time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="2.4 GiB" time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="144.0 MiB" time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="364.0 MiB" time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="1.6 GiB" time=2025-08-27T13:55:28.745+08:00 level=INFO source=backend.go:342 msg="total memory" size="9.6 GiB" time=2025-08-27T13:55:28.745+08:00 level=INFO source=sched.go:473 msg="loaded runners" count=1 time=2025-08-27T13:55:28.745+08:00 level=INFO source=server.go:1231 msg="waiting for llama runner to start responding" time=2025-08-27T13:55:28.746+08:00 level=INFO source=server.go:1265 msg="waiting for server to become available" status="llm server loading model" time=2025-08-27T13:55:29.997+08:00 level=INFO source=server.go:1269 msg="llama runner started in 1.69 seconds" C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error time=2025-08-27T13:55:30.212+08:00 level=ERROR source=server.go:1439 msg="post predict" error="Post \"http://127.0.0.1:53165/completion\": read tcp 127.0.0.1:53169->127.0.0.1:53165: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/08/27 - 13:55:30 | 200 | 2.0287446s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/08/27 - 13:56:00 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/08/27 - 13:56:00 | 200 | 0s | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/27 - 13:58:39 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/08/27 - 13:58:39 | 200 | 0s | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/27 - 13:58:44 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/08/27 - 13:58:44 | 200 | 27.4905ms | 127.0.0.1 | POST "/api/show" time=2025-08-27T13:58:49.294+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0179735 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=11528 runner.model=C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 time=2025-08-27T13:58:49.388+08:00 level=INFO source=server.go:383 msg="starting runner" cmd="C:\\Users\\94265\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\94265\\.ollama\\models\\blobs\\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 --port 53284" time=2025-08-27T13:58:49.401+08:00 level=INFO source=server.go:488 msg="system memory" total="31.4 GiB" free="15.5 GiB" free_swap="19.3 GiB" time=2025-08-27T13:58:49.402+08:00 level=INFO source=server.go:528 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=36 layers.split=[36] memory.available="[7.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.5 GiB" memory.required.partial="6.1 GiB" memory.required.kv="144.0 MiB" memory.required.allocations="[6.1 GiB]" memory.weights.total="5.7 GiB" memory.weights.repeating="5.2 GiB" memory.weights.nonrepeating="593.5 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" projector.weights="1.2 GiB" projector.graph="1.6 GiB" time=2025-08-27T13:58:49.426+08:00 level=INFO source=runner.go:1006 msg="starting ollama engine" time=2025-08-27T13:58:49.430+08:00 level=INFO source=runner.go:1043 msg="Server listening on 127.0.0.1:53284" time=2025-08-27T13:58:49.434+08:00 level=INFO source=runner.go:925 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:36[ID:GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 Layers:36(0..35)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-08-27T13:58:49.450+08:00 level=INFO source=ggml.go:130 msg="" architecture=qwen25vl file_type=F16 name="" description="" num_tensors=953 num_key_values=36 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 5080 Laptop GPU, compute capability 12.0, VMM: yes, ID: GPU-a5d2d457-1c84-896e-3d55-359d99f0b824 load_backend: loaded CUDA backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll time=2025-08-27T13:58:49.544+08:00 level=WARN source=sched.go:652 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2681944 runner.size="9.5 GiB" runner.vram="6.1 GiB" runner.parallel=1 runner.pid=11528 runner.model=C:\Users\94265\.ollama\models\blobs\sha256-f61e14330db38c990ce518ba5c27e8a080c64f9e8299b380ea4ecb8408efc119 load_backend: loaded CPU backend from C:\Users\94265\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2025-08-27T13:58:49.551+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-08-27T13:58:49.790+08:00 level=INFO source=ggml.go:486 msg="offloading 36 repeating layers to GPU" time=2025-08-27T13:58:49.790+08:00 level=INFO source=ggml.go:490 msg="offloading output layer to CPU" time=2025-08-27T13:58:49.790+08:00 level=INFO source=ggml.go:497 msg="offloaded 36/37 layers to GPU" time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:310 msg="model weights" device=CUDA0 size="5.2 GiB" time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:315 msg="model weights" device=CPU size="2.4 GiB" time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:321 msg="kv cache" device=CUDA0 size="144.0 MiB" time=2025-08-27T13:58:49.790+08:00 level=INFO source=backend.go:332 msg="compute graph" device=CUDA0 size="364.0 MiB" time=2025-08-27T13:58:49.791+08:00 level=INFO source=backend.go:337 msg="compute graph" device=CPU size="1.6 GiB" time=2025-08-27T13:58:49.791+08:00 level=INFO source=backend.go:342 msg="total memory" size="9.6 GiB" time=2025-08-27T13:58:49.791+08:00 level=INFO source=sched.go:473 msg="loaded runners" count=1 time=2025-08-27T13:58:49.791+08:00 level=INFO source=server.go:1231 msg="waiting for llama runner to start responding" time=2025-08-27T13:58:49.791+08:00 level=INFO source=server.go:1265 msg="waiting for server to become available" status="llm server loading model" time=2025-08-27T13:58:51.043+08:00 level=INFO source=server.go:1269 msg="llama runner started in 1.65 seconds" [GIN] 2025/08/27 - 13:58:51 | 200 | 6.7997025s | 127.0.0.1 | POST "/api/generate" C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:6930: fatal error time=2025-08-27T13:58:53.305+08:00 level=ERROR source=server.go:1439 msg="post predict" error="Post \"http://127.0.0.1:53284/completion\": read tcp 127.0.0.1:53288->127.0.0.1:53284: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/08/27 - 13:58:53 | 200 | 243.7775ms | 127.0.0.1 | POST "/api/chat" BUG，after i update ollama to 0.11.7 。 this problem happened。what should i do？

GiteaMirror commented

2026-04-12 20:14:51 -05:00

@gmcgarry commented on GitHub (Aug 27, 2025):

Roll back to 0.11.4 works for me.

@gmcgarry commented on GitHub (Aug 27, 2025): Roll back to 0.11.4 works for me.

GiteaMirror commented

2026-04-12 20:14:54 -05:00

@rick-github commented on GitHub (Aug 28, 2025):

@czj942650673 Your problem is unrelated, please stop posting and create a new issue.

@rick-github commented on GitHub (Aug 28, 2025): @czj942650673 Your problem is unrelated, please stop posting and create a new issue.

GiteaMirror commented

2026-04-12 20:14:54 -05:00

@MasseR commented on GitHub (Aug 28, 2025):

I think I might have the same issue on linux, but I'm not sure which part of the logs classifies this to be the same issue.

Aug 28 14:42:56 lissu systemd[1]: Starting Server for local large language models...
Aug 28 14:42:56 lissu systemd[1]: Started Server for local large language models.
Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.553+03:00 level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/lib/ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.554+03:00 level=INFO source=images.go:477 msg="total blobs: 23"
Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.554+03:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.555+03:00 level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.7)"
Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.555+03:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.556+03:00 level=INFO source=gpu.go:379 msg="no compatible GPUs were discovered"
Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.556+03:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="31.1 GiB" available="22.8 GiB"
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /var/lib/ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (version GGUF V3 (latest))
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   0:                       general.architecture str              = llama
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   1:                               general.type str              = model
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   2:                               general.name str              = Llama 3.2 3B Instruct
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   3:                           general.finetune str              = Instruct
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   4:                           general.basename str              = Llama-3.2
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   5:                         general.size_label str              = 3B
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   6:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   7:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   8:                          llama.block_count u32              = 28
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv   9:                       llama.context_length u32              = 131072
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  10:                     llama.embedding_length u32              = 3072
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  11:                  llama.feed_forward_length u32              = 8192
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  12:                 llama.attention.head_count u32              = 24
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  13:              llama.attention.head_count_kv u32              = 8
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  14:                       llama.rope.freq_base f32              = 500000.000000
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  15:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  16:                 llama.attention.key_length u32              = 128
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  17:               llama.attention.value_length u32              = 128
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  18:                          general.file_type u32              = 15
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  19:                           llama.vocab_size u32              = 128256
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  20:                 llama.rope.dimension_count u32              = 128
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = llama-bpe
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 128000
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 128009
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv  29:               general.quantization_version u32              = 2
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - type  f32:   58 tensors
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - type q4_K:  168 tensors
Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - type q6_K:   29 tensors
Aug 28 14:43:10 lissu ollama[10486]: print_info: file format = GGUF V3 (latest)
Aug 28 14:43:10 lissu ollama[10486]: print_info: file type   = Q4_K - Medium
Aug 28 14:43:10 lissu ollama[10486]: print_info: file size   = 1.87 GiB (5.01 BPW)
Aug 28 14:43:10 lissu ollama[10486]: load: printing all EOG tokens:
Aug 28 14:43:10 lissu ollama[10486]: load:   - 128001 ('<|end_of_text|>')
Aug 28 14:43:10 lissu ollama[10486]: load:   - 128008 ('<|eom_id|>')
Aug 28 14:43:10 lissu ollama[10486]: load:   - 128009 ('<|eot_id|>')
Aug 28 14:43:10 lissu ollama[10486]: load: special tokens cache size = 256
Aug 28 14:43:10 lissu ollama[10486]: load: token to piece cache size = 0.7999 MB
Aug 28 14:43:10 lissu ollama[10486]: print_info: arch             = llama
Aug 28 14:43:10 lissu ollama[10486]: print_info: vocab_only       = 1
Aug 28 14:43:10 lissu ollama[10486]: print_info: model type       = ?B
Aug 28 14:43:10 lissu ollama[10486]: print_info: model params     = 3.21 B
Aug 28 14:43:10 lissu ollama[10486]: print_info: general.name     = Llama 3.2 3B Instruct
Aug 28 14:43:10 lissu ollama[10486]: print_info: vocab type       = BPE
Aug 28 14:43:10 lissu ollama[10486]: print_info: n_vocab          = 128256
Aug 28 14:43:10 lissu ollama[10486]: print_info: n_merges         = 280147
Aug 28 14:43:10 lissu ollama[10486]: print_info: BOS token        = 128000 '<|begin_of_text|>'
Aug 28 14:43:10 lissu ollama[10486]: print_info: EOS token        = 128009 '<|eot_id|>'
Aug 28 14:43:10 lissu ollama[10486]: print_info: EOT token        = 128009 '<|eot_id|>'
Aug 28 14:43:10 lissu ollama[10486]: print_info: EOM token        = 128008 '<|eom_id|>'
Aug 28 14:43:10 lissu ollama[10486]: print_info: LF token         = 198 'Ċ'
Aug 28 14:43:10 lissu ollama[10486]: print_info: EOG token        = 128001 '<|end_of_text|>'
Aug 28 14:43:10 lissu ollama[10486]: print_info: EOG token        = 128008 '<|eom_id|>'
Aug 28 14:43:10 lissu ollama[10486]: print_info: EOG token        = 128009 '<|eot_id|>'
Aug 28 14:43:10 lissu ollama[10486]: print_info: max token length = 256
Aug 28 14:43:10 lissu ollama[10486]: llama_model_load: vocab only - skipping tensors
Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.412+03:00 level=INFO source=server.go:383 msg="starting runner" cmd="/nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama runner --model /var/lib/ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --port 37923"
Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.413+03:00 level=INFO source=server.go:488 msg="system memory" total="31.1 GiB" free="22.5 GiB" free_swap="32.0 GiB"
Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.413+03:00 level=INFO source=memory.go:36 msg="new model will fit in available VRAM across minimum required GPUs, loading" model=/var/lib/ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff library=cpu parallel=1 required="0 B" gpus=1
Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.413+03:00 level=INFO source=server.go:528 msg=offload library=cpu layers.requested=-1 layers.model=29 layers.offload=0 layers.split=[] memory.available="[22.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.6 GiB" memory.required.partial="0 B" memory.required.kv="448.0 MiB" memory.required.allocations="[2.6 GiB]" memory.weights.total="1.9 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="256.5 MiB" memory.graph.partial="570.7 MiB"
Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.422+03:00 level=INFO source=runner.go:864 msg="starting go runner"
Aug 28 14:43:10 lissu ollama[10486]: /build/source/ml/backend/ggml/ggml/src/ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(+0x1517d) [0x7fca2041e17d]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(ggml_print_backtrace+0x216) [0x7fca2041e626]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(ggml_abort+0x144) [0x7fca2041e7e4]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(+0x14650) [0x7fca2041d650]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0x472f) [0x7fca6a0df72f]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0x482d) [0x7fca6a0df82d]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(_dl_catch_exception+0x142) [0x7fca6a0dc5e2]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0xba94) [0x7fca6a0e6a94]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(_dl_catch_exception+0xa3) [0x7fca6a0dc543]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0xbe44) [0x7fca6a0e6e44]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/libc.so.6(+0x96764) [0x7fca69a96764]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(_dl_catch_exception+0xa3) [0x7fca6a0dc543]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0x1699) [0x7fca6a0dc699]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/libc.so.6(+0x961e3) [0x7fca69a961e3]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/libc.so.6(dlopen+0x6f) [0x7fca69a9682f]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11b6d4f]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11baf4f]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11b893c]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11b9c91]
Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x4a74e4]
Aug 28 14:43:10 lissu ollama[10486]: SIGABRT: abort
Aug 28 14:43:10 lissu ollama[10486]: PC=0x7fca69a9caac m=0 sigcode=18446744073709551610
Aug 28 14:43:10 lissu ollama[10486]: signal arrived during cgo execution
Aug 28 14:43:10 lissu ollama[10486]: goroutine 1 gp=0xc000002380 m=0 mp=0x216f9e0 [syscall]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.cgocall(0x118d4b0, 0xc000125710)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/cgocall.go:167 +0x4b fp=0xc0001256e8 sp=0xc0001256b0 pc=0x49c54b
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x344d87e0)
Aug 28 14:43:10 lissu ollama[10486]:         _cgo_gotypes.go:195 +0x3a fp=0xc000125710 sp=0xc0001256e8 pc=0x84b1ba
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc000046014, 0x44})
Aug 28 14:43:10 lissu ollama[10486]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0001257a8 sp=0xc000125710 pc=0x84ac55
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1()
Aug 28 14:43:10 lissu ollama[10486]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc000125a38 sp=0xc0001257a8 pc=0x84aaa6
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2()
Aug 28 14:43:10 lissu ollama[10486]:         sync/oncefunc.go:27 +0x62 fp=0xc000125a80 sp=0xc000125a38 pc=0x84a4a2
Aug 28 14:43:10 lissu ollama[10486]: sync.(*Once).doSlow(0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         sync/once.go:78 +0xab fp=0xc000125ad8 sp=0xc000125a80 pc=0x4b1dab
Aug 28 14:43:10 lissu ollama[10486]: sync.(*Once).Do(0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         sync/once.go:69 +0x19 fp=0xc000125af8 sp=0xc000125ad8 pc=0x4b1cd9
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3()
Aug 28 14:43:10 lissu ollama[10486]:         sync/oncefunc.go:32 +0x2d fp=0xc000125b28 sp=0xc000125af8 pc=0x84a40d
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/llama.BackendInit()
Aug 28 14:43:10 lissu ollama[10486]:         github.com/ollama/ollama/llama/llama.go:61 +0x16 fp=0xc000125b38 sp=0xc000125b28 pc=0x84f596
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc0000342c0, 0x4, 0x4})
Aug 28 14:43:10 lissu ollama[10486]:         github.com/ollama/ollama/runner/llamarunner/runner.go:866 +0x395 fp=0xc000125d08 sp=0xc000125b38 pc=0x91a875
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/runner.Execute({0xc0000342b0?, 0x0?, 0x0?})
Aug 28 14:43:10 lissu ollama[10486]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000125d30 sp=0xc000125d08 pc=0x9a5354
Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f3200?, {0x162f129?, 0x4?, 0x162f12d?})
Aug 28 14:43:10 lissu ollama[10486]:         github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000125d58 sp=0xc000125d30 pc=0x1109fa5
Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).execute(0xc00013af08, {0xc0006864c0, 0x4, 0x4})
Aug 28 14:43:10 lissu ollama[10486]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x894 fp=0xc000125e78 sp=0xc000125d58 pc=0x618d34
Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).ExecuteC(0xc000736908)
Aug 28 14:43:10 lissu ollama[10486]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000125f30 sp=0xc000125e78 pc=0x619585
Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).Execute(...)
Aug 28 14:43:10 lissu ollama[10486]:         github.com/spf13/cobra@v1.7.0/command.go:992
Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
Aug 28 14:43:10 lissu ollama[10486]:         github.com/spf13/cobra@v1.7.0/command.go:985
Aug 28 14:43:10 lissu ollama[10486]: main.main()
Aug 28 14:43:10 lissu ollama[10486]:         github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000125f50 sp=0xc000125f30 pc=0x110aa8d
Aug 28 14:43:10 lissu ollama[10486]: runtime.main()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:283 +0x28b fp=0xc000125fe0 sp=0xc000125f50 pc=0x46c46b
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000125fe8 sp=0xc000125fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000076fa8 sp=0xc000076f88 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.goparkunlock(...)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:441
Aug 28 14:43:10 lissu ollama[10486]: runtime.forcegchelper()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:348 +0xb3 fp=0xc000076fe0 sp=0xc000076fa8 pc=0x46c7b3
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000076fe8 sp=0xc000076fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.init.7 in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:336 +0x1a
Aug 28 14:43:10 lissu ollama[10486]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000077780 sp=0xc000077760 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.goparkunlock(...)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:441
Aug 28 14:43:10 lissu ollama[10486]: runtime.bgsweep(0xc0000a2000)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgcsweep.go:316 +0xdf fp=0xc0000777c8 sp=0xc000077780 pc=0x456f3f
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcenable.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:204 +0x25 fp=0xc0000777e0 sp=0xc0000777c8 pc=0x44b3a5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000777e8 sp=0xc0000777e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcenable in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:204 +0x66
Aug 28 14:43:10 lissu ollama[10486]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x10000?, 0x17f7dc8?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000077f78 sp=0xc000077f58 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.goparkunlock(...)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:441
Aug 28 14:43:10 lissu ollama[10486]: runtime.(*scavengerState).park(0x216cbc0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc000077fa8 sp=0xc000077f78 pc=0x454989
Aug 28 14:43:10 lissu ollama[10486]: runtime.bgscavenge(0xc0000a2000)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc000077fc8 sp=0xc000077fa8 pc=0x454f19
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcenable.gowrap2()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:205 +0x25 fp=0xc000077fe0 sp=0xc000077fc8 pc=0x44b345
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000077fe8 sp=0xc000077fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcenable in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:205 +0xa5
Aug 28 14:43:10 lissu ollama[10486]: goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000076688?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000076630 sp=0xc000076610 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.runfinq()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mfinal.go:196 +0x107 fp=0xc0000767e0 sp=0xc000076630 pc=0x44a367
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000767e8 sp=0xc0000767e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.createfing in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mfinal.go:166 +0x3d
Aug 28 14:43:10 lissu ollama[10486]: goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xc000225680?, 0xc000590018?, 0x60?, 0x87?, 0x586068?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000078718 sp=0xc0000786f8 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.chanrecv(0xc000044380, 0x0, 0x1)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/chan.go:664 +0x445 fp=0xc000078790 sp=0xc000078718 pc=0x43be25
Aug 28 14:43:10 lissu ollama[10486]: runtime.chanrecv1(0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/chan.go:506 +0x12 fp=0xc0000787b8 sp=0xc000078790 pc=0x43b9b2
Aug 28 14:43:10 lissu ollama[10486]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1797
Aug 28 14:43:10 lissu ollama[10486]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1800 +0x2f fp=0xc0000787e0 sp=0xc0000787b8 pc=0x44e4ef
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000787e8 sp=0xc0000787e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1795 +0x79
Aug 28 14:43:10 lissu ollama[10486]: goroutine 7 gp=0xc0001d0c40 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000078f38 sp=0xc000078f18 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc000078fc8 sp=0xc000078f38 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc000078fe0 sp=0xc000078fc8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000078fe8 sp=0xc000078fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 8 gp=0xc0001d0e00 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000079738 sp=0xc000079718 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000797c8 sp=0xc000079738 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc0000797e0 sp=0xc0000797c8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000797e8 sp=0xc0000797e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 9 gp=0xc0001d0fc0 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000079f38 sp=0xc000079f18 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc000079fc8 sp=0xc000079f38 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc000079fe0 sp=0xc000079fc8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000079fe8 sp=0xc000079fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 10 gp=0xc0001d1180 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000072738 sp=0xc000072718 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000727c8 sp=0xc000072738 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc0000727e0 sp=0xc0000727c8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 11 gp=0xc0001d1340 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000072f38 sp=0xc000072f18 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc000072fc8 sp=0xc000072f38 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc000072fe0 sp=0xc000072fc8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 12 gp=0xc0001d1500 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000073738 sp=0xc000073718 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000737c8 sp=0xc000073738 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc00011a738 sp=0xc00011a718 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc00011a7c8 sp=0xc00011a738 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc00011a7e0 sp=0xc00011a7c8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00011a7e8 sp=0xc00011a7e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x221c880?, 0x1?, 0x4c?, 0x3e?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc00011af38 sp=0xc00011af18 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc00011afc8 sp=0xc00011af38 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc00011afe0 sp=0xc00011afc8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00011afe8 sp=0xc00011afe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 13 gp=0xc0001d16c0 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd86965ee8?, 0x3?, 0x2a?, 0x5?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000073f38 sp=0xc000073f18 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc000073fc8 sp=0xc000073f38 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 14 gp=0xc0001d1880 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd8696633b?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000074738 sp=0xc000074718 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000747c8 sp=0xc000074738 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc0000747e0 sp=0xc0000747c8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 15 gp=0xc0001d1a40 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd869465df?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: goroutine 16 gp=0xc0001d1c00 m=nil [GC worker (idle)]:
Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd86947849?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x49f9ce
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0)
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x44d809
Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x44d6e5
Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({})
Aug 28 14:43:10 lissu ollama[10486]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x4a7861
Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 28 14:43:10 lissu ollama[10486]:         runtime/mgc.go:1339 +0x105
Aug 28 14:43:10 lissu ollama[10486]: rax    0x0
Aug 28 14:43:10 lissu ollama[10486]: rbx    0x29d1
Aug 28 14:43:10 lissu ollama[10486]: rcx    0x7fca69a9caac
Aug 28 14:43:10 lissu ollama[10486]: rdx    0x6
Aug 28 14:43:10 lissu ollama[10486]: rdi    0x29d1
Aug 28 14:43:10 lissu ollama[10486]: rsi    0x29d1
Aug 28 14:43:10 lissu ollama[10486]: rbp    0x7ffe88dfd240
Aug 28 14:43:10 lissu ollama[10486]: rsp    0x7ffe88dfd200
Aug 28 14:43:10 lissu ollama[10486]: r8     0x0
Aug 28 14:43:10 lissu ollama[10486]: r9     0x0
Aug 28 14:43:10 lissu ollama[10486]: r10    0x8
Aug 28 14:43:10 lissu ollama[10486]: r11    0x246
Aug 28 14:43:10 lissu ollama[10486]: r12    0x7fca6a07c780
Aug 28 14:43:10 lissu ollama[10486]: r13    0x7fca2048ca70
Aug 28 14:43:10 lissu ollama[10486]: r14    0x6
Aug 28 14:43:10 lissu ollama[10486]: r15    0x7fca204a4f58
Aug 28 14:43:10 lissu ollama[10486]: rip    0x7fca69a9caac
Aug 28 14:43:10 lissu ollama[10486]: rflags 0x246
Aug 28 14:43:10 lissu ollama[10486]: cs     0x33
Aug 28 14:43:10 lissu ollama[10486]: fs     0x0
Aug 28 14:43:10 lissu ollama[10486]: gs     0x0
Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.431+03:00 level=ERROR source=server.go:409 msg="llama runner terminated" error="exit status 2"

@MasseR commented on GitHub (Aug 28, 2025): I think I might have the same issue on linux, but I'm not sure which part of the logs classifies this to be the same issue. ``` Aug 28 14:42:56 lissu systemd[1]: Starting Server for local large language models... Aug 28 14:42:56 lissu systemd[1]: Started Server for local large language models. Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.553+03:00 level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/lib/ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.554+03:00 level=INFO source=images.go:477 msg="total blobs: 23" Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.554+03:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0" Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.555+03:00 level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.7)" Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.555+03:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.556+03:00 level=INFO source=gpu.go:379 msg="no compatible GPUs were discovered" Aug 28 14:42:56 lissu ollama[10486]: time=2025-08-28T14:42:56.556+03:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="31.1 GiB" available="22.8 GiB" Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /var/lib/ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (version GGUF V3 (latest)) Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 0: general.architecture str = llama Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 1: general.type str = model Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 2: general.name str = Llama 3.2 3B Instruct Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 3: general.finetune str = Instruct Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 4: general.basename str = Llama-3.2 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 5: general.size_label str = 3B Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 6: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 7: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 8: llama.block_count u32 = 28 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 9: llama.context_length u32 = 131072 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 10: llama.embedding_length u32 = 3072 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 11: llama.feed_forward_length u32 = 8192 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 12: llama.attention.head_count u32 = 24 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 13: llama.attention.head_count_kv u32 = 8 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 14: llama.rope.freq_base f32 = 500000.000000 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 15: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 16: llama.attention.key_length u32 = 128 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 17: llama.attention.value_length u32 = 128 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 18: general.file_type u32 = 15 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 19: llama.vocab_size u32 = 128256 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 20: llama.rope.dimension_count u32 = 128 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 22: tokenizer.ggml.pre str = llama-bpe Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 128000 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 128009 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 28: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - kv 29: general.quantization_version u32 = 2 Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - type f32: 58 tensors Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - type q4_K: 168 tensors Aug 28 14:43:10 lissu ollama[10486]: llama_model_loader: - type q6_K: 29 tensors Aug 28 14:43:10 lissu ollama[10486]: print_info: file format = GGUF V3 (latest) Aug 28 14:43:10 lissu ollama[10486]: print_info: file type = Q4_K - Medium Aug 28 14:43:10 lissu ollama[10486]: print_info: file size = 1.87 GiB (5.01 BPW) Aug 28 14:43:10 lissu ollama[10486]: load: printing all EOG tokens: Aug 28 14:43:10 lissu ollama[10486]: load: - 128001 ('<|end_of_text|>') Aug 28 14:43:10 lissu ollama[10486]: load: - 128008 ('<|eom_id|>') Aug 28 14:43:10 lissu ollama[10486]: load: - 128009 ('<|eot_id|>') Aug 28 14:43:10 lissu ollama[10486]: load: special tokens cache size = 256 Aug 28 14:43:10 lissu ollama[10486]: load: token to piece cache size = 0.7999 MB Aug 28 14:43:10 lissu ollama[10486]: print_info: arch = llama Aug 28 14:43:10 lissu ollama[10486]: print_info: vocab_only = 1 Aug 28 14:43:10 lissu ollama[10486]: print_info: model type = ?B Aug 28 14:43:10 lissu ollama[10486]: print_info: model params = 3.21 B Aug 28 14:43:10 lissu ollama[10486]: print_info: general.name = Llama 3.2 3B Instruct Aug 28 14:43:10 lissu ollama[10486]: print_info: vocab type = BPE Aug 28 14:43:10 lissu ollama[10486]: print_info: n_vocab = 128256 Aug 28 14:43:10 lissu ollama[10486]: print_info: n_merges = 280147 Aug 28 14:43:10 lissu ollama[10486]: print_info: BOS token = 128000 '<|begin_of_text|>' Aug 28 14:43:10 lissu ollama[10486]: print_info: EOS token = 128009 '<|eot_id|>' Aug 28 14:43:10 lissu ollama[10486]: print_info: EOT token = 128009 '<|eot_id|>' Aug 28 14:43:10 lissu ollama[10486]: print_info: EOM token = 128008 '<|eom_id|>' Aug 28 14:43:10 lissu ollama[10486]: print_info: LF token = 198 'Ċ' Aug 28 14:43:10 lissu ollama[10486]: print_info: EOG token = 128001 '<|end_of_text|>' Aug 28 14:43:10 lissu ollama[10486]: print_info: EOG token = 128008 '<|eom_id|>' Aug 28 14:43:10 lissu ollama[10486]: print_info: EOG token = 128009 '<|eot_id|>' Aug 28 14:43:10 lissu ollama[10486]: print_info: max token length = 256 Aug 28 14:43:10 lissu ollama[10486]: llama_model_load: vocab only - skipping tensors Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.412+03:00 level=INFO source=server.go:383 msg="starting runner" cmd="/nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama runner --model /var/lib/ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --port 37923" Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.413+03:00 level=INFO source=server.go:488 msg="system memory" total="31.1 GiB" free="22.5 GiB" free_swap="32.0 GiB" Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.413+03:00 level=INFO source=memory.go:36 msg="new model will fit in available VRAM across minimum required GPUs, loading" model=/var/lib/ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff library=cpu parallel=1 required="0 B" gpus=1 Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.413+03:00 level=INFO source=server.go:528 msg=offload library=cpu layers.requested=-1 layers.model=29 layers.offload=0 layers.split=[] memory.available="[22.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.6 GiB" memory.required.partial="0 B" memory.required.kv="448.0 MiB" memory.required.allocations="[2.6 GiB]" memory.weights.total="1.9 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="256.5 MiB" memory.graph.partial="570.7 MiB" Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.422+03:00 level=INFO source=runner.go:864 msg="starting go runner" Aug 28 14:43:10 lissu ollama[10486]: /build/source/ml/backend/ggml/ggml/src/ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(+0x1517d) [0x7fca2041e17d] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(ggml_print_backtrace+0x216) [0x7fca2041e626] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(ggml_abort+0x144) [0x7fca2041e7e4] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/lib/ollama/libggml-base.so(+0x14650) [0x7fca2041d650] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0x472f) [0x7fca6a0df72f] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0x482d) [0x7fca6a0df82d] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(_dl_catch_exception+0x142) [0x7fca6a0dc5e2] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0xba94) [0x7fca6a0e6a94] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(_dl_catch_exception+0xa3) [0x7fca6a0dc543] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0xbe44) [0x7fca6a0e6e44] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/libc.so.6(+0x96764) [0x7fca69a96764] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(_dl_catch_exception+0xa3) [0x7fca6a0dc543] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/ld-linux-x86-64.so.2(+0x1699) [0x7fca6a0dc699] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/libc.so.6(+0x961e3) [0x7fca69a961e3] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/8p33is69mjdw3bi1wmi8v2zpsxir8nwd-glibc-2.40-66/lib/libc.so.6(dlopen+0x6f) [0x7fca69a9682f] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11b6d4f] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11baf4f] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11b893c] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x11b9c91] Aug 28 14:43:10 lissu ollama[10486]: /nix/store/6vfxb3liai6vhgm6dxy7cv7cz6j871sn-ollama-0.11.7/bin/ollama() [0x4a74e4] Aug 28 14:43:10 lissu ollama[10486]: SIGABRT: abort Aug 28 14:43:10 lissu ollama[10486]: PC=0x7fca69a9caac m=0 sigcode=18446744073709551610 Aug 28 14:43:10 lissu ollama[10486]: signal arrived during cgo execution Aug 28 14:43:10 lissu ollama[10486]: goroutine 1 gp=0xc000002380 m=0 mp=0x216f9e0 [syscall]: Aug 28 14:43:10 lissu ollama[10486]: runtime.cgocall(0x118d4b0, 0xc000125710) Aug 28 14:43:10 lissu ollama[10486]: runtime/cgocall.go:167 +0x4b fp=0xc0001256e8 sp=0xc0001256b0 pc=0x49c54b Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x344d87e0) Aug 28 14:43:10 lissu ollama[10486]: _cgo_gotypes.go:195 +0x3a fp=0xc000125710 sp=0xc0001256e8 pc=0x84b1ba Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc000046014, 0x44}) Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0001257a8 sp=0xc000125710 pc=0x84ac55 Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1() Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc000125a38 sp=0xc0001257a8 pc=0x84aaa6 Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2() Aug 28 14:43:10 lissu ollama[10486]: sync/oncefunc.go:27 +0x62 fp=0xc000125a80 sp=0xc000125a38 pc=0x84a4a2 Aug 28 14:43:10 lissu ollama[10486]: sync.(*Once).doSlow(0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: sync/once.go:78 +0xab fp=0xc000125ad8 sp=0xc000125a80 pc=0x4b1dab Aug 28 14:43:10 lissu ollama[10486]: sync.(*Once).Do(0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: sync/once.go:69 +0x19 fp=0xc000125af8 sp=0xc000125ad8 pc=0x4b1cd9 Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3() Aug 28 14:43:10 lissu ollama[10486]: sync/oncefunc.go:32 +0x2d fp=0xc000125b28 sp=0xc000125af8 pc=0x84a40d Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/llama.BackendInit() Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/llama/llama.go:61 +0x16 fp=0xc000125b38 sp=0xc000125b28 pc=0x84f596 Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc0000342c0, 0x4, 0x4}) Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/runner/llamarunner/runner.go:866 +0x395 fp=0xc000125d08 sp=0xc000125b38 pc=0x91a875 Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/runner.Execute({0xc0000342b0?, 0x0?, 0x0?}) Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000125d30 sp=0xc000125d08 pc=0x9a5354 Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f3200?, {0x162f129?, 0x4?, 0x162f12d?}) Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000125d58 sp=0xc000125d30 pc=0x1109fa5 Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).execute(0xc00013af08, {0xc0006864c0, 0x4, 0x4}) Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x894 fp=0xc000125e78 sp=0xc000125d58 pc=0x618d34 Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).ExecuteC(0xc000736908) Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000125f30 sp=0xc000125e78 pc=0x619585 Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).Execute(...) Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra@v1.7.0/command.go:992 Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra.(*Command).ExecuteContext(...) Aug 28 14:43:10 lissu ollama[10486]: github.com/spf13/cobra@v1.7.0/command.go:985 Aug 28 14:43:10 lissu ollama[10486]: main.main() Aug 28 14:43:10 lissu ollama[10486]: github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000125f50 sp=0xc000125f30 pc=0x110aa8d Aug 28 14:43:10 lissu ollama[10486]: runtime.main() Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:283 +0x28b fp=0xc000125fe0 sp=0xc000125f50 pc=0x46c46b Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000125fe8 sp=0xc000125fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000076fa8 sp=0xc000076f88 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.goparkunlock(...) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:441 Aug 28 14:43:10 lissu ollama[10486]: runtime.forcegchelper() Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:348 +0xb3 fp=0xc000076fe0 sp=0xc000076fa8 pc=0x46c7b3 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000076fe8 sp=0xc000076fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.init.7 in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:336 +0x1a Aug 28 14:43:10 lissu ollama[10486]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000077780 sp=0xc000077760 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.goparkunlock(...) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:441 Aug 28 14:43:10 lissu ollama[10486]: runtime.bgsweep(0xc0000a2000) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgcsweep.go:316 +0xdf fp=0xc0000777c8 sp=0xc000077780 pc=0x456f3f Aug 28 14:43:10 lissu ollama[10486]: runtime.gcenable.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:204 +0x25 fp=0xc0000777e0 sp=0xc0000777c8 pc=0x44b3a5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000777e8 sp=0xc0000777e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcenable in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:204 +0x66 Aug 28 14:43:10 lissu ollama[10486]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x10000?, 0x17f7dc8?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000077f78 sp=0xc000077f58 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.goparkunlock(...) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:441 Aug 28 14:43:10 lissu ollama[10486]: runtime.(*scavengerState).park(0x216cbc0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgcscavenge.go:425 +0x49 fp=0xc000077fa8 sp=0xc000077f78 pc=0x454989 Aug 28 14:43:10 lissu ollama[10486]: runtime.bgscavenge(0xc0000a2000) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgcscavenge.go:658 +0x59 fp=0xc000077fc8 sp=0xc000077fa8 pc=0x454f19 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcenable.gowrap2() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:205 +0x25 fp=0xc000077fe0 sp=0xc000077fc8 pc=0x44b345 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000077fe8 sp=0xc000077fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcenable in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:205 +0xa5 Aug 28 14:43:10 lissu ollama[10486]: goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000076688?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000076630 sp=0xc000076610 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.runfinq() Aug 28 14:43:10 lissu ollama[10486]: runtime/mfinal.go:196 +0x107 fp=0xc0000767e0 sp=0xc000076630 pc=0x44a367 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000767e8 sp=0xc0000767e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.createfing in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mfinal.go:166 +0x3d Aug 28 14:43:10 lissu ollama[10486]: goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xc000225680?, 0xc000590018?, 0x60?, 0x87?, 0x586068?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000078718 sp=0xc0000786f8 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.chanrecv(0xc000044380, 0x0, 0x1) Aug 28 14:43:10 lissu ollama[10486]: runtime/chan.go:664 +0x445 fp=0xc000078790 sp=0xc000078718 pc=0x43be25 Aug 28 14:43:10 lissu ollama[10486]: runtime.chanrecv1(0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/chan.go:506 +0x12 fp=0xc0000787b8 sp=0xc000078790 pc=0x43b9b2 Aug 28 14:43:10 lissu ollama[10486]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1797 Aug 28 14:43:10 lissu ollama[10486]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1800 +0x2f fp=0xc0000787e0 sp=0xc0000787b8 pc=0x44e4ef Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000787e8 sp=0xc0000787e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1795 +0x79 Aug 28 14:43:10 lissu ollama[10486]: goroutine 7 gp=0xc0001d0c40 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000078f38 sp=0xc000078f18 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc000078fc8 sp=0xc000078f38 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc000078fe0 sp=0xc000078fc8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000078fe8 sp=0xc000078fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 8 gp=0xc0001d0e00 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000079738 sp=0xc000079718 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc0000797c8 sp=0xc000079738 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc0000797e0 sp=0xc0000797c8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000797e8 sp=0xc0000797e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 9 gp=0xc0001d0fc0 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000079f38 sp=0xc000079f18 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc000079fc8 sp=0xc000079f38 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc000079fe0 sp=0xc000079fc8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000079fe8 sp=0xc000079fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 10 gp=0xc0001d1180 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000072738 sp=0xc000072718 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc0000727c8 sp=0xc000072738 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc0000727e0 sp=0xc0000727c8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 11 gp=0xc0001d1340 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000072f38 sp=0xc000072f18 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc000072fc8 sp=0xc000072f38 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc000072fe0 sp=0xc000072fc8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 12 gp=0xc0001d1500 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000073738 sp=0xc000073718 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc0000737c8 sp=0xc000073738 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc00011a738 sp=0xc00011a718 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc00011a7c8 sp=0xc00011a738 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc00011a7e0 sp=0xc00011a7c8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00011a7e8 sp=0xc00011a7e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0x221c880?, 0x1?, 0x4c?, 0x3e?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc00011af38 sp=0xc00011af18 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc00011afc8 sp=0xc00011af38 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc00011afe0 sp=0xc00011afc8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00011afe8 sp=0xc00011afe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 13 gp=0xc0001d16c0 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd86965ee8?, 0x3?, 0x2a?, 0x5?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000073f38 sp=0xc000073f18 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc000073fc8 sp=0xc000073f38 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 14 gp=0xc0001d1880 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd8696633b?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000074738 sp=0xc000074718 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc0000747c8 sp=0xc000074738 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc0000747e0 sp=0xc0000747c8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 15 gp=0xc0001d1a40 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd869465df?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: goroutine 16 gp=0xc0001d1c00 m=nil [GC worker (idle)]: Aug 28 14:43:10 lissu ollama[10486]: runtime.gopark(0xfd86947849?, 0x0?, 0x0?, 0x0?, 0x0?) Aug 28 14:43:10 lissu ollama[10486]: runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x49f9ce Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkWorker(0xc0000457a0) Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x44d809 Aug 28 14:43:10 lissu ollama[10486]: runtime.gcBgMarkStartWorkers.gowrap1() Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x44d6e5 Aug 28 14:43:10 lissu ollama[10486]: runtime.goexit({}) Aug 28 14:43:10 lissu ollama[10486]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x4a7861 Aug 28 14:43:10 lissu ollama[10486]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Aug 28 14:43:10 lissu ollama[10486]: runtime/mgc.go:1339 +0x105 Aug 28 14:43:10 lissu ollama[10486]: rax 0x0 Aug 28 14:43:10 lissu ollama[10486]: rbx 0x29d1 Aug 28 14:43:10 lissu ollama[10486]: rcx 0x7fca69a9caac Aug 28 14:43:10 lissu ollama[10486]: rdx 0x6 Aug 28 14:43:10 lissu ollama[10486]: rdi 0x29d1 Aug 28 14:43:10 lissu ollama[10486]: rsi 0x29d1 Aug 28 14:43:10 lissu ollama[10486]: rbp 0x7ffe88dfd240 Aug 28 14:43:10 lissu ollama[10486]: rsp 0x7ffe88dfd200 Aug 28 14:43:10 lissu ollama[10486]: r8 0x0 Aug 28 14:43:10 lissu ollama[10486]: r9 0x0 Aug 28 14:43:10 lissu ollama[10486]: r10 0x8 Aug 28 14:43:10 lissu ollama[10486]: r11 0x246 Aug 28 14:43:10 lissu ollama[10486]: r12 0x7fca6a07c780 Aug 28 14:43:10 lissu ollama[10486]: r13 0x7fca2048ca70 Aug 28 14:43:10 lissu ollama[10486]: r14 0x6 Aug 28 14:43:10 lissu ollama[10486]: r15 0x7fca204a4f58 Aug 28 14:43:10 lissu ollama[10486]: rip 0x7fca69a9caac Aug 28 14:43:10 lissu ollama[10486]: rflags 0x246 Aug 28 14:43:10 lissu ollama[10486]: cs 0x33 Aug 28 14:43:10 lissu ollama[10486]: fs 0x0 Aug 28 14:43:10 lissu ollama[10486]: gs 0x0 Aug 28 14:43:10 lissu ollama[10486]: time=2025-08-28T14:43:10.431+03:00 level=ERROR source=server.go:409 msg="llama runner terminated" error="exit status 2" ```

GiteaMirror commented

2026-04-12 20:14:55 -05:00

@HilaryTraut commented on GitHub (Aug 29, 2025):

Updated to Mac OS 15.6.1 - no change. Updated Ollama to 0.11.8 - no change. Downgraded to 0.11.4 as @gmcgarry did, queries just hang in GUI. Server logs after downgrade below (though likely separate issue than the present assert).

time=2025-08-29T09:54:08.423-06:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/htraut/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 4096 --batch-size 512 --threads 4 --no-mmap --parallel 1 --port 55667" time=2025-08-29T09:54:08.426-06:00 level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-08-29T09:54:08.426-06:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-29T09:54:08.427-06:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-08-29T09:54:08.451-06:00 level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-08-29T09:54:08.452-06:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:55667" time=2025-08-29T09:54:08.523-06:00 level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30 load_backend: loaded CPU backend from /Applications/Ollama.app/Contents/Resources/libggml-cpu-icelake.so time=2025-08-29T09:54:08.627-06:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.SSE3=1 CPU.1.SSSE3=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:365 msg="offloading 0 repeating layers to GPU" time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:369 msg="offloading output layer to CPU" time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:376 msg="offloaded 0/25 layers to GPU" time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:379 msg="model weights" buffer=CPU size="12.8 GiB" time=2025-08-29T09:54:08.680-06:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" time=2025-08-29T09:54:08.756-06:00 level=INFO source=ggml.go:668 msg="compute graph" backend=CPU buffer_type=CPU size="1.2 GiB" time=2025-08-29T09:54:31.569-06:00 level=INFO source=server.go:637 msg="llama runner started in 23.15 seconds" time=2025-08-29T09:55:08.164-06:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:55667/completion\": context canceled" [GIN] 2025/08/29 - 09:55:08 | 200 | 59.981530666s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/08/29 - 09:55:20 | 200 | 823.169µs | 127.0.0.1 | GET "/api/version" [GIN] 2025/08/29 - 10:09:07 | 200 | 3.110302ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:09:25 | 200 | 85.253µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/29 - 10:09:25 | 200 | 660.756µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:10:48 | 200 | 863.283µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:53:56 | 200 | 5.134404ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:58:40 | 200 | 6.292201ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:58:40 | 200 | 138.396052ms | 127.0.0.1 | POST "/api/show"

@HilaryTraut commented on GitHub (Aug 29, 2025): Updated to Mac OS 15.6.1 - no change. Updated Ollama to 0.11.8 - no change. Downgraded to 0.11.4 as @gmcgarry did, queries just hang in GUI. Server logs after downgrade below (though likely separate issue than the present assert). `time=2025-08-29T09:54:08.423-06:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/htraut/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 4096 --batch-size 512 --threads 4 --no-mmap --parallel 1 --port 55667" time=2025-08-29T09:54:08.426-06:00 level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-08-29T09:54:08.426-06:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-29T09:54:08.427-06:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-08-29T09:54:08.451-06:00 level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-08-29T09:54:08.452-06:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:55667" time=2025-08-29T09:54:08.523-06:00 level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30 load_backend: loaded CPU backend from /Applications/Ollama.app/Contents/Resources/libggml-cpu-icelake.so time=2025-08-29T09:54:08.627-06:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.SSE3=1 CPU.1.SSSE3=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:365 msg="offloading 0 repeating layers to GPU" time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:369 msg="offloading output layer to CPU" time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:376 msg="offloaded 0/25 layers to GPU" time=2025-08-29T09:54:08.629-06:00 level=INFO source=ggml.go:379 msg="model weights" buffer=CPU size="12.8 GiB" time=2025-08-29T09:54:08.680-06:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" time=2025-08-29T09:54:08.756-06:00 level=INFO source=ggml.go:668 msg="compute graph" backend=CPU buffer_type=CPU size="1.2 GiB" time=2025-08-29T09:54:31.569-06:00 level=INFO source=server.go:637 msg="llama runner started in 23.15 seconds" time=2025-08-29T09:55:08.164-06:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:55667/completion\": context canceled" [GIN] 2025/08/29 - 09:55:08 | 200 | 59.981530666s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/08/29 - 09:55:20 | 200 | 823.169µs | 127.0.0.1 | GET "/api/version" [GIN] 2025/08/29 - 10:09:07 | 200 | 3.110302ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:09:25 | 200 | 85.253µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/29 - 10:09:25 | 200 | 660.756µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:10:48 | 200 | 863.283µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:53:56 | 200 | 5.134404ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:58:40 | 200 | 6.292201ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/29 - 10:58:40 | 200 | 138.396052ms | 127.0.0.1 | POST "/api/show"`

GiteaMirror commented

2026-04-12 20:14:57 -05:00

@MrSom3body commented on GitHub (Sep 1, 2025):

I'm not 100% sure if it's the same issue, but it seems to fail with the same exception on NixOS: ollama.log

@MrSom3body commented on GitHub (Sep 1, 2025): I'm not 100% sure if it's the same issue, but it seems to fail with the same exception on NixOS: [ollama.log](https://gist.github.com/MrSom3body/b06888d441abed93cf8435051b76a6ef)

GiteaMirror commented

2026-04-12 20:14:58 -05:00

@dhiltgen commented on GitHub (Sep 2, 2025):

The fix for the following error will be in 0.11.9

ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed

@dhiltgen commented on GitHub (Sep 2, 2025): The fix for the following error will be in 0.11.9 ``` ggml.cpp:22: GGML_ASSERT(prev != ggml_uncaught_exception) failed ```

GiteaMirror referenced this issue

2026-04-13 00:04:07 -05:00

[PR #8019] Delete redundancy code when never happends. #12591

GiteaMirror referenced this issue

2026-04-16 06:17:05 -05:00

[PR #8019] Delete redundancy code when never happends. #17862

GiteaMirror referenced this issue

2026-04-19 16:47:11 -05:00

[PR #8019] Delete redundancy code when never happends. #23131

GiteaMirror referenced this issue

2026-04-22 23:07:45 -05:00

[PR #8019] Delete redundancy code when never happends. #38464

GiteaMirror referenced this issue

2026-04-24 23:25:05 -05:00

[PR #8019] Delete redundancy code when never happends. #43839

GiteaMirror referenced this issue

2026-04-29 14:14:00 -05:00

[PR #8019] Delete redundancy code when never happends. #59288

GiteaMirror referenced this issue

2026-05-05 07:12:55 -05:00

[PR #8019] Delete redundancy code when never happends. #74885

Sign in to join this conversation.

Branches Tags

main

hoyyeva/anthropic-local-image-path

dhiltgen/ci

dhiltgen/llama-runner

parth-remove-claude-desktop-launch

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#8019