github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11491] gemma3:12b stop working after update to ollama 0.9.6 #7590

New Issue
Closed
opened 2026-04-12 19:40:42 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 19:40:42 -05:00
Owner
Copy Link

Originally created by @DanoPTT on GitHub (Jul 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11491

What is the issue?

I update ollama (auto update) on widnows 11, and now gemma3:12b do not works. When I try to run it, I get following error. I try to delete and download model again, but still error.
Error: llama runner process has terminated: error:fault

Relevant log output

time=2025-07-22T10:59:51.306+02:00 level=INFO source=routes.go:1235 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://0.0.0.0:11434 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:\\ollama\\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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=2025-07-22T10:59:51.308+02:00 level=INFO source=images.go:476 msg="total blobs: 5"
time=2025-07-22T10:59:51.309+02:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0"
time=2025-07-22T10:59:51.309+02:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)"
time=2025-07-22T10:59:51.309+02:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-07-22T10:59:51.309+02:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-07-22T10:59:51.309+02:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12
time=2025-07-22T10:59:51.458+02:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" overhead="890.0 MiB"
time=2025-07-22T10:59:51.460+02:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" total="15.9 GiB" available="14.7 GiB"
[GIN] 2025/07/22 - 10:59:51 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/07/22 - 10:59:51 | 200 |    135.4839ms |       127.0.0.1 | POST     "/api/show"
time=2025-07-22T10:59:52.021+02:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de gpu=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a parallel=2 available=15804137472 required="11.0 GiB"
time=2025-07-22T10:59:52.036+02:00 level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="17.7 GiB" free_swap="18.1 GiB"
time=2025-07-22T10:59:52.036+02:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[14.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.0 GiB" memory.required.partial="11.0 GiB" memory.required.kv="1.3 GiB" memory.required.allocations="[11.0 GiB]" memory.weights.total="6.8 GiB" memory.weights.repeating="6.0 GiB" memory.weights.nonrepeating="787.5 MiB" memory.graph.full="519.5 MiB" memory.graph.partial="1.3 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
time=2025-07-22T10:59:52.125+02:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\ollama\\ollama.exe runner --ollama-engine --model C:\\ollama\\Models\\blobs\\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de --ctx-size 8192 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 2 --port 64672"
time=2025-07-22T10:59:52.131+02:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-07-22T10:59:52.131+02:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-07-22T10:59:52.131+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
time=2025-07-22T10:59:52.170+02:00 level=INFO source=runner.go:925 msg="starting ollama engine"
time=2025-07-22T10:59:52.171+02:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:64672"
time=2025-07-22T10:59:52.241+02:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=37
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 5060 Ti, compute capability 12.0, VMM: yes
load_backend: loaded CUDA backend from C:\ollama\lib\ollama\ggml-cuda.dll
load_backend: loaded CPU backend from C:\ollama\lib\ollama\ggml-cpu-haswell.dll
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 5060 Ti, compute capability 12.0, VMM: yes
load_backend: loaded CUDA backend from C:\ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2025-07-22T10:59:52.359+02:00 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.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 CUDA.1.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.1.USE_GRAPHS=1 CUDA.1.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-07-22T10:59:52.384+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
unexpected fault address 0x3ae000000
fatal error: fault
[signal 0xc0000005 code=0x0 addr=0x3ae000000 pc=0x7ff6bf7d7180]

goroutine 24 gp=0xc000003a40 m=10 mp=0xc000700008 [running]:
runtime.throw({0x7ff6c0a277d7?, 0x0?})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/panic.go:1096 +0x4d fp=0xc0000490d0 sp=0xc0000490a0 pc=0x7ff6bf8461ed
runtime.sigpanic()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/signal_windows.go:414 +0xd0 fp=0xc000049118 sp=0xc0000490d0 pc=0x7ff6bf828f10
indexbytebody()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/bytealg/indexbyte_amd64.s:131 +0xe0 fp=0xc000049120 sp=0xc000049118 pc=0x7ff6bf7d7180
runtime.findnull(0xc0000491a0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/string.go:577 +0x79 fp=0xc000049178 sp=0xc000049120 pc=0x7ff6bf82e039
runtime.gostring(0x3ae000000)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/string.go:363 +0x1c fp=0xc0000491b0 sp=0xc000049178 pc=0x7ff6bf848d5c
github.com/ollama/ollama/ml/backend/ggml._Cfunc_GoString(...)
	_cgo_gotypes.go:299
github.com/ollama/ollama/ml/backend/ggml.New({0xc000136000, 0x5e}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0})
	C:/a/ollama/ollama/ml/backend/ggml/ggml.go:158 +0x1359 fp=0xc000049c18 sp=0xc0000491b0 pc=0x7ff6bfc98499
github.com/ollama/ollama/ml.NewBackend({0xc000136000, 0x5e}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0})
	C:/a/ollama/ollama/ml/backend.go:209 +0xb1 fp=0xc000049c70 sp=0xc000049c18 pc=0x7ff6bfc89091
github.com/ollama/ollama/model.New({0xc000136000?, 0x0?}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0})
	C:/a/ollama/ollama/model/model.go:102 +0x8f fp=0xc000049d68 sp=0xc000049c70 pc=0x7ff6bfca7f6f
github.com/ollama/ollama/runner/ollamarunner.(*Server).initModel(0xc00073dd40, {0xc000136000?, 0x0?}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0}, ...)
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:841 +0x8d fp=0xc000049dc8 sp=0xc000049d68 pc=0x7ff6bfd49fed
github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc00073dd40, {0x7ff6c0c03510, 0xc00037e1e0}, {0xc000136000?, 0x0?}, {0x6, 0x0, 0x31, {0x0, 0x0, ...}, ...}, ...)
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:878 +0xb8 fp=0xc000049f20 sp=0xc000049dc8 pc=0x7ff6bfd4a358
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:959 +0xc7 fp=0xc000049fe0 sp=0xc000049f20 pc=0x7ff6bfd4b787
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x7ff6bf84db01
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:959 +0xa11

goroutine 1 gp=0xc0000021c0 m=nil [IO wait]:
runtime.gopark(0x7ff6bf84f300?, 0x7ff6c1555500?, 0x20?, 0x80?, 0xc0000880cc?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc0000a9508 sp=0xc0000a94e8 pc=0x7ff6bf84630e
runtime.netpollblock(0x248?, 0xbf7e0446?, 0xf6?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0000a9540 sp=0xc0000a9508 pc=0x7ff6bf80bf37
internal/poll.runtime_pollWait(0x1896c45d138, 0x72)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:351 +0x85 fp=0xc0000a9560 sp=0xc0000a9540 pc=0x7ff6bf8454a5
internal/poll.(*pollDesc).wait(0x7ff6bf8da293?, 0x7ff6bf7f2776?, 0x0)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000a9588 sp=0xc0000a9560 pc=0x7ff6bf8db887
internal/poll.execIO(0xc000088020, 0xc0000a9630)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:177 +0x105 fp=0xc0000a9600 sp=0xc0000a9588 pc=0x7ff6bf8dcce5
internal/poll.(*FD).acceptOne(0xc000088008, 0x410, {0xc0000a00f0?, 0xc0000a9690?, 0x7ff6bf8e49a5?}, 0xc0000a96c4?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:946 +0x65 fp=0xc0000a9660 sp=0xc0000a9600 pc=0x7ff6bf8e1265
internal/poll.(*FD).Accept(0xc000088008, 0xc0000a9810)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:980 +0x1b6 fp=0xc0000a9718 sp=0xc0000a9660 pc=0x7ff6bf8e1596
net.(*netFD).accept(0xc000088008)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/fd_windows.go:182 +0x4b fp=0xc0000a9830 sp=0xc0000a9718 pc=0x7ff6bf9520ab
net.(*TCPListener).accept(0xc000418000)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/tcpsock_posix.go:159 +0x1b fp=0xc0000a9880 sp=0xc0000a9830 pc=0x7ff6bf9680fb
net.(*TCPListener).Accept(0xc000418000)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/tcpsock.go:380 +0x30 fp=0xc0000a98b0 sp=0xc0000a9880 pc=0x7ff6bf966eb0
net/http.(*onceCloseListener).Accept(0xc00059e480?)
	<autogenerated>:1 +0x24 fp=0xc0000a98c8 sp=0xc0000a98b0 pc=0x7ff6bfb802a4
net/http.(*Server).Serve(0xc000092100, {0x7ff6c0c00f20, 0xc000418000})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:3424 +0x30c fp=0xc0000a99f8 sp=0xc0000a98c8 pc=0x7ff6bfb57b6c
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc00013c030, 0xf, 0x1d})
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:984 +0xe09 fp=0xc0000a9d08 sp=0xc0000a99f8 pc=0x7ff6bfd4b3e9
github.com/ollama/ollama/runner.Execute({0xc00013c010?, 0x0?, 0x0?})
	C:/a/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc0000a9d30 sp=0xc0000a9d08 pc=0x7ff6bfd4bce9
github.com/ollama/ollama/cmd.NewCLI.func2(0xc000092f00?, {0x7ff6c0a26384?, 0x4?, 0x7ff6c0a26388?})
	C:/a/ollama/ollama/cmd/cmd.go:1529 +0x45 fp=0xc0000a9d58 sp=0xc0000a9d30 pc=0x7ff6c04aa765
github.com/spf13/cobra.(*Command).execute(0xc0005a0f08, {0xc000093100, 0x10, 0x10})
	C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0000a9e78 sp=0xc0000a9d58 pc=0x7ff6bf9ccb7c
github.com/spf13/cobra.(*Command).ExecuteC(0xc00073b508)
	C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0000a9f30 sp=0xc0000a9e78 pc=0x7ff6bf9cd3c5
github.com/spf13/cobra.(*Command).Execute(...)
	C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
	C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
	C:/a/ollama/ollama/main.go:12 +0x4d fp=0xc0000a9f50 sp=0xc0000a9f30 pc=0x7ff6c04ab1ed
runtime.main()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:283 +0x27d fp=0xc0000a9fe0 sp=0xc0000a9f50 pc=0x7ff6bf814f1d
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a9fe8 sp=0xc0000a9fe0 pc=0x7ff6bf84db01

goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00006ffa8 sp=0xc00006ff88 pc=0x7ff6bf84630e
runtime.goparkunlock(...)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441
runtime.forcegchelper()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:348 +0xb8 fp=0xc00006ffe0 sp=0xc00006ffa8 pc=0x7ff6bf815238
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x7ff6bf84db01
created by runtime.init.7 in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000071f80 sp=0xc000071f60 pc=0x7ff6bf84630e
runtime.goparkunlock(...)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441
runtime.bgsweep(0xc00007e000)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgcsweep.go:316 +0xdf fp=0xc000071fc8 sp=0xc000071f80 pc=0x7ff6bf7fdfff
runtime.gcenable.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:204 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x7ff6bf7f23c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x7ff6bf84db01
created by runtime.gcenable in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x7ff6c0bee160?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x7ff6bf84630e
runtime.goparkunlock(...)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441
runtime.(*scavengerState).park(0x7ff6c157bc00)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x7ff6bf7fba49
runtime.bgscavenge(0xc00007e000)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x7ff6bf7fbfd9
runtime.gcenable.gowrap2()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x7ff6bf7f2365
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff6bf84db01
created by runtime.gcenable in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:205 +0xa5

goroutine 18 gp=0xc000106380 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000081e30 sp=0xc000081e10 pc=0x7ff6bf84630e
runtime.runfinq()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mfinal.go:196 +0x107 fp=0xc000081fe0 sp=0xc000081e30 pc=0x7ff6bf7f1347
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff6bf84db01
created by runtime.createfing in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mfinal.go:166 +0x3d

goroutine 19 gp=0xc000106e00 m=nil [chan receive]:
runtime.gopark(0xc0001c37c0?, 0xc0001201c8?, 0x60?, 0x3f?, 0x7ff6bf93b0e8?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000073f18 sp=0xc000073ef8 pc=0x7ff6bf84630e
runtime.chanrecv(0xc000108310, 0x0, 0x1)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/chan.go:664 +0x445 fp=0xc000073f90 sp=0xc000073f18 pc=0x7ff6bf7e2d85
runtime.chanrecv1(0x7ff6bf815080?, 0xc000073f76?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/chan.go:506 +0x12 fp=0xc000073fb8 sp=0xc000073f90 pc=0x7ff6bf7e2912
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1799 +0x2f fp=0xc000073fe0 sp=0xc000073fb8 pc=0x7ff6bf7f55ef
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x7ff6bf84db01
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1794 +0x85

goroutine 20 gp=0xc000107180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000083f38 sp=0xc000083f18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000083fc8 sp=0xc000083f38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 5 gp=0xc000003180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000087f38 sp=0xc000087f18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000087fc8 sp=0xc000087f38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000087fe0 sp=0xc000087fc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc000107340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 6 gp=0xc000003340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]:
runtime.gopark(0x137dbe824fb4c?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 22 gp=0xc000107500 m=nil [GC worker (idle)]:
runtime.gopark(0x137dbe824fb4c?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000484380 m=nil [GC worker (idle)]:
runtime.gopark(0x7ff6c15ca6e0?, 0x1?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00008bf38 sp=0xc00008bf18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00008bfc8 sp=0xc00008bf38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00008bfe0 sp=0xc00008bfc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00008bfe8 sp=0xc00008bfe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc000484540 m=nil [GC worker (idle)]:
runtime.gopark(0x137dbe824fb4c?, 0x1?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00008df38 sp=0xc00008df18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00008dfc8 sp=0xc00008df38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00008dfe0 sp=0xc00008dfc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00008dfe8 sp=0xc00008dfe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 7 gp=0xc000003500 m=nil [GC worker (idle)]:
runtime.gopark(0x137dbe824fb4c?, 0x3?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000091f38 sp=0xc000091f18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000091fc8 sp=0xc000091f38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 23 gp=0xc0001076c0 m=nil [GC worker (idle)]:
runtime.gopark(0x137dbe824fb4c?, 0x0?, 0x0?, 0x0?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc000484700 m=nil [GC worker (idle)]:
runtime.gopark(0x137dbe824fb4c?, 0x1?, 0x30?, 0x45?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff6bf84630e
runtime.gcBgMarkWorker(0xc000109730)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff6bf7f48e9
runtime.gcBgMarkStartWorkers.gowrap1()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff6bf7f47c5
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff6bf84db01
created by runtime.gcBgMarkStartWorkers in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105

goroutine 25 gp=0xc000003c00 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0xa0?, 0x1d?, 0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000475ed0 sp=0xc000475eb0 pc=0x7ff6bf84630e
runtime.goparkunlock(...)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441
runtime.semacquire1(0xc00073dd48, 0x0, 0x1, 0x0, 0x18)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/sema.go:188 +0x22f fp=0xc000475f38 sp=0xc000475ed0 pc=0x7ff6bf82764f
sync.runtime_SemacquireWaitGroup(0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/sema.go:110 +0x25 fp=0xc000475f70 sp=0xc000475f38 pc=0x7ff6bf8479e5
sync.(*WaitGroup).Wait(0x0?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/sync/waitgroup.go:118 +0x48 fp=0xc000475f98 sp=0xc000475f70 pc=0x7ff6bf85b9c8
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00073dd40, {0x7ff6c0c03510, 0xc00037e1e0})
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:355 +0x25 fp=0xc000475fb8 sp=0xc000475f98 pc=0x7ff6bfd45f05
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap2()
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:960 +0x28 fp=0xc000475fe0 sp=0xc000475fb8 pc=0x7ff6bfd4b688
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000475fe8 sp=0xc000475fe0 pc=0x7ff6bf84db01
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
	C:/a/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74

goroutine 8 gp=0xc000484a80 m=nil [IO wait]:
runtime.gopark(0x0?, 0xc000587420?, 0xc8?, 0x74?, 0xc0005874cc?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc0000a58c8 sp=0xc0000a58a8 pc=0x7ff6bf84630e
runtime.netpollblock(0x274?, 0xbf7e0446?, 0xf6?)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0000a5900 sp=0xc0000a58c8 pc=0x7ff6bf80bf37
internal/poll.runtime_pollWait(0x1896c45d020, 0x72)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:351 +0x85 fp=0xc0000a5920 sp=0xc0000a5900 pc=0x7ff6bf8454a5
internal/poll.(*pollDesc).wait(0x7ff6bfa0bb57?, 0xc0000a5970?, 0x0)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000a5948 sp=0xc0000a5920 pc=0x7ff6bf8db887
internal/poll.execIO(0xc000587420, 0x7ff6c0a9b1a0)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:177 +0x105 fp=0xc0000a59c0 sp=0xc0000a5948 pc=0x7ff6bf8dcce5
internal/poll.(*FD).Read(0xc000587408, {0xc001c04000, 0x1000, 0x1000})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:438 +0x29b fp=0xc0000a5a60 sp=0xc0000a59c0 pc=0x7ff6bf8dd9bb
net.(*netFD).Read(0xc000587408, {0xc001c04000?, 0xc0000a5ad0?, 0x7ff6bf8dbd45?})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/fd_posix.go:55 +0x25 fp=0xc0000a5aa8 sp=0xc0000a5a60 pc=0x7ff6bf9501c5
net.(*conn).Read(0xc00060c030, {0xc001c04000?, 0x0?, 0x0?})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/net.go:194 +0x45 fp=0xc0000a5af0 sp=0xc0000a5aa8 pc=0x7ff6bf95f6a5
net/http.(*connReader).Read(0xc000210090, {0xc001c04000, 0x1000, 0x1000})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:798 +0x159 fp=0xc0000a5b40 sp=0xc0000a5af0 pc=0x7ff6bfb4ca19
bufio.(*Reader).fill(0xc0007681e0)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/bufio/bufio.go:113 +0x103 fp=0xc0000a5b78 sp=0xc0000a5b40 pc=0x7ff6bf975ee3
bufio.(*Reader).Peek(0xc0007681e0, 0x4)
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/bufio/bufio.go:152 +0x53 fp=0xc0000a5b98 sp=0xc0000a5b78 pc=0x7ff6bf976013
net/http.(*conn).serve(0xc00059e480, {0x7ff6c0c034d8, 0xc000177cb0})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:2137 +0x785 fp=0xc0000a5fb8 sp=0xc0000a5b98 pc=0x7ff6bfb52805
net/http.(*Server).Serve.gowrap3()
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:3454 +0x28 fp=0xc0000a5fe0 sp=0xc0000a5fb8 pc=0x7ff6bfb57f68
runtime.goexit({})
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a5fe8 sp=0xc0000a5fe0 pc=0x7ff6bf84db01
created by net/http.(*Server).Serve in goroutine 1
	C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:3454 +0x485
time=2025-07-22T10:59:52.495+02:00 level=ERROR source=server.go:464 msg="llama runner terminated" error="exit status 2"
time=2025-07-22T10:59:52.634+02:00 level=ERROR source=sched.go:489 msg="error loading llama server" error="llama runner process has terminated: error:fault"
[GIN] 2025/07/22 - 10:59:52 | 500 |    845.8154ms |       127.0.0.1 | POST     "/api/generate"
time=2025-07-22T10:59:57.648+02:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0136605 runner.size="11.0 GiB" runner.vram="11.0 GiB" runner.parallel=2 runner.pid=22620 runner.model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de
time=2025-07-22T10:59:57.898+02:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2637297 runner.size="11.0 GiB" runner.vram="11.0 GiB" runner.parallel=2 runner.pid=22620 runner.model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de
time=2025-07-22T10:59:58.148+02:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.513495 runner.size="11.0 GiB" runner.vram="11.0 GiB" runner.parallel=2 runner.pid=22620 runner.model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @DanoPTT on GitHub (Jul 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11491 ### What is the issue? I update ollama (auto update) on widnows 11, and now gemma3:12b do not works. When I try to run it, I get following error. I try to delete and download model again, but still error. Error: llama runner process has terminated: error:fault ### Relevant log output ```shell time=2025-07-22T10:59:51.306+02:00 level=INFO source=routes.go:1235 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://0.0.0.0:11434 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:\\ollama\\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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=2025-07-22T10:59:51.308+02:00 level=INFO source=images.go:476 msg="total blobs: 5" time=2025-07-22T10:59:51.309+02:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0" time=2025-07-22T10:59:51.309+02:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)" time=2025-07-22T10:59:51.309+02:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-07-22T10:59:51.309+02:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-07-22T10:59:51.309+02:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12 time=2025-07-22T10:59:51.458+02:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" overhead="890.0 MiB" time=2025-07-22T10:59:51.460+02:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" total="15.9 GiB" available="14.7 GiB" [GIN] 2025/07/22 - 10:59:51 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/07/22 - 10:59:51 | 200 | 135.4839ms | 127.0.0.1 | POST "/api/show" time=2025-07-22T10:59:52.021+02:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de gpu=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a parallel=2 available=15804137472 required="11.0 GiB" time=2025-07-22T10:59:52.036+02:00 level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="17.7 GiB" free_swap="18.1 GiB" time=2025-07-22T10:59:52.036+02:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[14.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.0 GiB" memory.required.partial="11.0 GiB" memory.required.kv="1.3 GiB" memory.required.allocations="[11.0 GiB]" memory.weights.total="6.8 GiB" memory.weights.repeating="6.0 GiB" memory.weights.nonrepeating="787.5 MiB" memory.graph.full="519.5 MiB" memory.graph.partial="1.3 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" time=2025-07-22T10:59:52.125+02:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\ollama\\ollama.exe runner --ollama-engine --model C:\\ollama\\Models\\blobs\\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de --ctx-size 8192 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 2 --port 64672" time=2025-07-22T10:59:52.131+02:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-07-22T10:59:52.131+02:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-07-22T10:59:52.131+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" time=2025-07-22T10:59:52.170+02:00 level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-07-22T10:59:52.171+02:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:64672" time=2025-07-22T10:59:52.241+02:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=37 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 5060 Ti, compute capability 12.0, VMM: yes load_backend: loaded CUDA backend from C:\ollama\lib\ollama\ggml-cuda.dll load_backend: loaded CPU backend from C:\ollama\lib\ollama\ggml-cpu-haswell.dll 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 5060 Ti, compute capability 12.0, VMM: yes load_backend: loaded CUDA backend from C:\ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2025-07-22T10:59:52.359+02:00 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.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 CUDA.1.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.1.USE_GRAPHS=1 CUDA.1.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-07-22T10:59:52.384+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" unexpected fault address 0x3ae000000 fatal error: fault [signal 0xc0000005 code=0x0 addr=0x3ae000000 pc=0x7ff6bf7d7180] goroutine 24 gp=0xc000003a40 m=10 mp=0xc000700008 [running]: runtime.throw({0x7ff6c0a277d7?, 0x0?}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/panic.go:1096 +0x4d fp=0xc0000490d0 sp=0xc0000490a0 pc=0x7ff6bf8461ed runtime.sigpanic() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/signal_windows.go:414 +0xd0 fp=0xc000049118 sp=0xc0000490d0 pc=0x7ff6bf828f10 indexbytebody() C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/bytealg/indexbyte_amd64.s:131 +0xe0 fp=0xc000049120 sp=0xc000049118 pc=0x7ff6bf7d7180 runtime.findnull(0xc0000491a0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/string.go:577 +0x79 fp=0xc000049178 sp=0xc000049120 pc=0x7ff6bf82e039 runtime.gostring(0x3ae000000) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/string.go:363 +0x1c fp=0xc0000491b0 sp=0xc000049178 pc=0x7ff6bf848d5c github.com/ollama/ollama/ml/backend/ggml._Cfunc_GoString(...) _cgo_gotypes.go:299 github.com/ollama/ollama/ml/backend/ggml.New({0xc000136000, 0x5e}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0}) C:/a/ollama/ollama/ml/backend/ggml/ggml.go:158 +0x1359 fp=0xc000049c18 sp=0xc0000491b0 pc=0x7ff6bfc98499 github.com/ollama/ollama/ml.NewBackend({0xc000136000, 0x5e}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0}) C:/a/ollama/ollama/ml/backend.go:209 +0xb1 fp=0xc000049c70 sp=0xc000049c18 pc=0x7ff6bfc89091 github.com/ollama/ollama/model.New({0xc000136000?, 0x0?}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0}) C:/a/ollama/ollama/model/model.go:102 +0x8f fp=0xc000049d68 sp=0xc000049c70 pc=0x7ff6bfca7f6f github.com/ollama/ollama/runner/ollamarunner.(*Server).initModel(0xc00073dd40, {0xc000136000?, 0x0?}, {0x6, 0x0, 0x31, {0x0, 0x0, 0x0}, 0x0}, ...) C:/a/ollama/ollama/runner/ollamarunner/runner.go:841 +0x8d fp=0xc000049dc8 sp=0xc000049d68 pc=0x7ff6bfd49fed github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc00073dd40, {0x7ff6c0c03510, 0xc00037e1e0}, {0xc000136000?, 0x0?}, {0x6, 0x0, 0x31, {0x0, 0x0, ...}, ...}, ...) C:/a/ollama/ollama/runner/ollamarunner/runner.go:878 +0xb8 fp=0xc000049f20 sp=0xc000049dc8 pc=0x7ff6bfd4a358 github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() C:/a/ollama/ollama/runner/ollamarunner/runner.go:959 +0xc7 fp=0xc000049fe0 sp=0xc000049f20 pc=0x7ff6bfd4b787 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x7ff6bf84db01 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 C:/a/ollama/ollama/runner/ollamarunner/runner.go:959 +0xa11 goroutine 1 gp=0xc0000021c0 m=nil [IO wait]: runtime.gopark(0x7ff6bf84f300?, 0x7ff6c1555500?, 0x20?, 0x80?, 0xc0000880cc?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc0000a9508 sp=0xc0000a94e8 pc=0x7ff6bf84630e runtime.netpollblock(0x248?, 0xbf7e0446?, 0xf6?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0000a9540 sp=0xc0000a9508 pc=0x7ff6bf80bf37 internal/poll.runtime_pollWait(0x1896c45d138, 0x72) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:351 +0x85 fp=0xc0000a9560 sp=0xc0000a9540 pc=0x7ff6bf8454a5 internal/poll.(*pollDesc).wait(0x7ff6bf8da293?, 0x7ff6bf7f2776?, 0x0) C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000a9588 sp=0xc0000a9560 pc=0x7ff6bf8db887 internal/poll.execIO(0xc000088020, 0xc0000a9630) C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:177 +0x105 fp=0xc0000a9600 sp=0xc0000a9588 pc=0x7ff6bf8dcce5 internal/poll.(*FD).acceptOne(0xc000088008, 0x410, {0xc0000a00f0?, 0xc0000a9690?, 0x7ff6bf8e49a5?}, 0xc0000a96c4?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:946 +0x65 fp=0xc0000a9660 sp=0xc0000a9600 pc=0x7ff6bf8e1265 internal/poll.(*FD).Accept(0xc000088008, 0xc0000a9810) C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:980 +0x1b6 fp=0xc0000a9718 sp=0xc0000a9660 pc=0x7ff6bf8e1596 net.(*netFD).accept(0xc000088008) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/fd_windows.go:182 +0x4b fp=0xc0000a9830 sp=0xc0000a9718 pc=0x7ff6bf9520ab net.(*TCPListener).accept(0xc000418000) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/tcpsock_posix.go:159 +0x1b fp=0xc0000a9880 sp=0xc0000a9830 pc=0x7ff6bf9680fb net.(*TCPListener).Accept(0xc000418000) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/tcpsock.go:380 +0x30 fp=0xc0000a98b0 sp=0xc0000a9880 pc=0x7ff6bf966eb0 net/http.(*onceCloseListener).Accept(0xc00059e480?) <autogenerated>:1 +0x24 fp=0xc0000a98c8 sp=0xc0000a98b0 pc=0x7ff6bfb802a4 net/http.(*Server).Serve(0xc000092100, {0x7ff6c0c00f20, 0xc000418000}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:3424 +0x30c fp=0xc0000a99f8 sp=0xc0000a98c8 pc=0x7ff6bfb57b6c github.com/ollama/ollama/runner/ollamarunner.Execute({0xc00013c030, 0xf, 0x1d}) C:/a/ollama/ollama/runner/ollamarunner/runner.go:984 +0xe09 fp=0xc0000a9d08 sp=0xc0000a99f8 pc=0x7ff6bfd4b3e9 github.com/ollama/ollama/runner.Execute({0xc00013c010?, 0x0?, 0x0?}) C:/a/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc0000a9d30 sp=0xc0000a9d08 pc=0x7ff6bfd4bce9 github.com/ollama/ollama/cmd.NewCLI.func2(0xc000092f00?, {0x7ff6c0a26384?, 0x4?, 0x7ff6c0a26388?}) C:/a/ollama/ollama/cmd/cmd.go:1529 +0x45 fp=0xc0000a9d58 sp=0xc0000a9d30 pc=0x7ff6c04aa765 github.com/spf13/cobra.(*Command).execute(0xc0005a0f08, {0xc000093100, 0x10, 0x10}) C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0000a9e78 sp=0xc0000a9d58 pc=0x7ff6bf9ccb7c github.com/spf13/cobra.(*Command).ExecuteC(0xc00073b508) C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0000a9f30 sp=0xc0000a9e78 pc=0x7ff6bf9cd3c5 github.com/spf13/cobra.(*Command).Execute(...) C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) C:/Users/runneradmin/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 main.main() C:/a/ollama/ollama/main.go:12 +0x4d fp=0xc0000a9f50 sp=0xc0000a9f30 pc=0x7ff6c04ab1ed runtime.main() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:283 +0x27d fp=0xc0000a9fe0 sp=0xc0000a9f50 pc=0x7ff6bf814f1d runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a9fe8 sp=0xc0000a9fe0 pc=0x7ff6bf84db01 goroutine 2 gp=0xc0000028c0 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00006ffa8 sp=0xc00006ff88 pc=0x7ff6bf84630e runtime.goparkunlock(...) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441 runtime.forcegchelper() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:348 +0xb8 fp=0xc00006ffe0 sp=0xc00006ffa8 pc=0x7ff6bf815238 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x7ff6bf84db01 created by runtime.init.7 in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000002c40 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000071f80 sp=0xc000071f60 pc=0x7ff6bf84630e runtime.goparkunlock(...) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441 runtime.bgsweep(0xc00007e000) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgcsweep.go:316 +0xdf fp=0xc000071fc8 sp=0xc000071f80 pc=0x7ff6bf7fdfff runtime.gcenable.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:204 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x7ff6bf7f23c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x7ff6bf84db01 created by runtime.gcenable in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000002e00 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x7ff6c0bee160?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x7ff6bf84630e runtime.goparkunlock(...) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441 runtime.(*scavengerState).park(0x7ff6c157bc00) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x7ff6bf7fba49 runtime.bgscavenge(0xc00007e000) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x7ff6bf7fbfd9 runtime.gcenable.gowrap2() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x7ff6bf7f2365 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x7ff6bf84db01 created by runtime.gcenable in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:205 +0xa5 goroutine 18 gp=0xc000106380 m=nil [finalizer wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000081e30 sp=0xc000081e10 pc=0x7ff6bf84630e runtime.runfinq() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mfinal.go:196 +0x107 fp=0xc000081fe0 sp=0xc000081e30 pc=0x7ff6bf7f1347 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x7ff6bf84db01 created by runtime.createfing in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mfinal.go:166 +0x3d goroutine 19 gp=0xc000106e00 m=nil [chan receive]: runtime.gopark(0xc0001c37c0?, 0xc0001201c8?, 0x60?, 0x3f?, 0x7ff6bf93b0e8?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000073f18 sp=0xc000073ef8 pc=0x7ff6bf84630e runtime.chanrecv(0xc000108310, 0x0, 0x1) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/chan.go:664 +0x445 fp=0xc000073f90 sp=0xc000073f18 pc=0x7ff6bf7e2d85 runtime.chanrecv1(0x7ff6bf815080?, 0xc000073f76?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/chan.go:506 +0x12 fp=0xc000073fb8 sp=0xc000073f90 pc=0x7ff6bf7e2912 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1799 +0x2f fp=0xc000073fe0 sp=0xc000073fb8 pc=0x7ff6bf7f55ef runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x7ff6bf84db01 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1794 +0x85 goroutine 20 gp=0xc000107180 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000083f38 sp=0xc000083f18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000083fc8 sp=0xc000083f38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 5 gp=0xc000003180 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000087f38 sp=0xc000087f18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000087fc8 sp=0xc000087f38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000087fe0 sp=0xc000087fc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 21 gp=0xc000107340 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 6 gp=0xc000003340 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00008ff38 sp=0xc00008ff18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00008ffc8 sp=0xc00008ff38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00008ffe0 sp=0xc00008ffc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00008ffe8 sp=0xc00008ffe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]: runtime.gopark(0x137dbe824fb4c?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 22 gp=0xc000107500 m=nil [GC worker (idle)]: runtime.gopark(0x137dbe824fb4c?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000489f38 sp=0xc000489f18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000489fc8 sp=0xc000489f38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000489fe0 sp=0xc000489fc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000489fe8 sp=0xc000489fe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000484380 m=nil [GC worker (idle)]: runtime.gopark(0x7ff6c15ca6e0?, 0x1?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00008bf38 sp=0xc00008bf18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00008bfc8 sp=0xc00008bf38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00008bfe0 sp=0xc00008bfc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00008bfe8 sp=0xc00008bfe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc000484540 m=nil [GC worker (idle)]: runtime.gopark(0x137dbe824fb4c?, 0x1?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00008df38 sp=0xc00008df18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00008dfc8 sp=0xc00008df38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00008dfe0 sp=0xc00008dfc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00008dfe8 sp=0xc00008dfe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 7 gp=0xc000003500 m=nil [GC worker (idle)]: runtime.gopark(0x137dbe824fb4c?, 0x3?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000091f38 sp=0xc000091f18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000091fc8 sp=0xc000091f38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000091fe0 sp=0xc000091fc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000091fe8 sp=0xc000091fe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 23 gp=0xc0001076c0 m=nil [GC worker (idle)]: runtime.gopark(0x137dbe824fb4c?, 0x0?, 0x0?, 0x0?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000473f38 sp=0xc000473f18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc000473fc8 sp=0xc000473f38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc000473fe0 sp=0xc000473fc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000473fe8 sp=0xc000473fe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc000484700 m=nil [GC worker (idle)]: runtime.gopark(0x137dbe824fb4c?, 0x1?, 0x30?, 0x45?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc00046ff38 sp=0xc00046ff18 pc=0x7ff6bf84630e runtime.gcBgMarkWorker(0xc000109730) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1423 +0xe9 fp=0xc00046ffc8 sp=0xc00046ff38 pc=0x7ff6bf7f48e9 runtime.gcBgMarkStartWorkers.gowrap1() C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x25 fp=0xc00046ffe0 sp=0xc00046ffc8 pc=0x7ff6bf7f47c5 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc00046ffe8 sp=0xc00046ffe0 pc=0x7ff6bf84db01 created by runtime.gcBgMarkStartWorkers in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/mgc.go:1339 +0x105 goroutine 25 gp=0xc000003c00 m=nil [sync.WaitGroup.Wait]: runtime.gopark(0x0?, 0x0?, 0xa0?, 0x1d?, 0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc000475ed0 sp=0xc000475eb0 pc=0x7ff6bf84630e runtime.goparkunlock(...) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:441 runtime.semacquire1(0xc00073dd48, 0x0, 0x1, 0x0, 0x18) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/sema.go:188 +0x22f fp=0xc000475f38 sp=0xc000475ed0 pc=0x7ff6bf82764f sync.runtime_SemacquireWaitGroup(0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/sema.go:110 +0x25 fp=0xc000475f70 sp=0xc000475f38 pc=0x7ff6bf8479e5 sync.(*WaitGroup).Wait(0x0?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/sync/waitgroup.go:118 +0x48 fp=0xc000475f98 sp=0xc000475f70 pc=0x7ff6bf85b9c8 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00073dd40, {0x7ff6c0c03510, 0xc00037e1e0}) C:/a/ollama/ollama/runner/ollamarunner/runner.go:355 +0x25 fp=0xc000475fb8 sp=0xc000475f98 pc=0x7ff6bfd45f05 github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap2() C:/a/ollama/ollama/runner/ollamarunner/runner.go:960 +0x28 fp=0xc000475fe0 sp=0xc000475fb8 pc=0x7ff6bfd4b688 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc000475fe8 sp=0xc000475fe0 pc=0x7ff6bf84db01 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 C:/a/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74 goroutine 8 gp=0xc000484a80 m=nil [IO wait]: runtime.gopark(0x0?, 0xc000587420?, 0xc8?, 0x74?, 0xc0005874cc?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/proc.go:435 +0xce fp=0xc0000a58c8 sp=0xc0000a58a8 pc=0x7ff6bf84630e runtime.netpollblock(0x274?, 0xbf7e0446?, 0xf6?) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:575 +0xf7 fp=0xc0000a5900 sp=0xc0000a58c8 pc=0x7ff6bf80bf37 internal/poll.runtime_pollWait(0x1896c45d020, 0x72) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/netpoll.go:351 +0x85 fp=0xc0000a5920 sp=0xc0000a5900 pc=0x7ff6bf8454a5 internal/poll.(*pollDesc).wait(0x7ff6bfa0bb57?, 0xc0000a5970?, 0x0) C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000a5948 sp=0xc0000a5920 pc=0x7ff6bf8db887 internal/poll.execIO(0xc000587420, 0x7ff6c0a9b1a0) C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:177 +0x105 fp=0xc0000a59c0 sp=0xc0000a5948 pc=0x7ff6bf8dcce5 internal/poll.(*FD).Read(0xc000587408, {0xc001c04000, 0x1000, 0x1000}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/internal/poll/fd_windows.go:438 +0x29b fp=0xc0000a5a60 sp=0xc0000a59c0 pc=0x7ff6bf8dd9bb net.(*netFD).Read(0xc000587408, {0xc001c04000?, 0xc0000a5ad0?, 0x7ff6bf8dbd45?}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/fd_posix.go:55 +0x25 fp=0xc0000a5aa8 sp=0xc0000a5a60 pc=0x7ff6bf9501c5 net.(*conn).Read(0xc00060c030, {0xc001c04000?, 0x0?, 0x0?}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/net.go:194 +0x45 fp=0xc0000a5af0 sp=0xc0000a5aa8 pc=0x7ff6bf95f6a5 net/http.(*connReader).Read(0xc000210090, {0xc001c04000, 0x1000, 0x1000}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:798 +0x159 fp=0xc0000a5b40 sp=0xc0000a5af0 pc=0x7ff6bfb4ca19 bufio.(*Reader).fill(0xc0007681e0) C:/hostedtoolcache/windows/go/1.24.0/x64/src/bufio/bufio.go:113 +0x103 fp=0xc0000a5b78 sp=0xc0000a5b40 pc=0x7ff6bf975ee3 bufio.(*Reader).Peek(0xc0007681e0, 0x4) C:/hostedtoolcache/windows/go/1.24.0/x64/src/bufio/bufio.go:152 +0x53 fp=0xc0000a5b98 sp=0xc0000a5b78 pc=0x7ff6bf976013 net/http.(*conn).serve(0xc00059e480, {0x7ff6c0c034d8, 0xc000177cb0}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:2137 +0x785 fp=0xc0000a5fb8 sp=0xc0000a5b98 pc=0x7ff6bfb52805 net/http.(*Server).Serve.gowrap3() C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:3454 +0x28 fp=0xc0000a5fe0 sp=0xc0000a5fb8 pc=0x7ff6bfb57f68 runtime.goexit({}) C:/hostedtoolcache/windows/go/1.24.0/x64/src/runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a5fe8 sp=0xc0000a5fe0 pc=0x7ff6bf84db01 created by net/http.(*Server).Serve in goroutine 1 C:/hostedtoolcache/windows/go/1.24.0/x64/src/net/http/server.go:3454 +0x485 time=2025-07-22T10:59:52.495+02:00 level=ERROR source=server.go:464 msg="llama runner terminated" error="exit status 2" time=2025-07-22T10:59:52.634+02:00 level=ERROR source=sched.go:489 msg="error loading llama server" error="llama runner process has terminated: error:fault" [GIN] 2025/07/22 - 10:59:52 | 500 | 845.8154ms | 127.0.0.1 | POST "/api/generate" time=2025-07-22T10:59:57.648+02:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0136605 runner.size="11.0 GiB" runner.vram="11.0 GiB" runner.parallel=2 runner.pid=22620 runner.model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de time=2025-07-22T10:59:57.898+02:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2637297 runner.size="11.0 GiB" runner.vram="11.0 GiB" runner.parallel=2 runner.pid=22620 runner.model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de time=2025-07-22T10:59:58.148+02:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.513495 runner.size="11.0 GiB" runner.vram="11.0 GiB" runner.parallel=2 runner.pid=22620 runner.model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 19:40:42 -05:00
GiteaMirror commented 2026-04-12 19:40:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2025):

load_backend: loaded CUDA backend from C:\ollama\lib\ollama\ggml-cuda.dll
load_backend: loaded CUDA backend from C:\ollama\lib\ollama\cuda_v12\ggml-cuda.dll

#11211

Delete C:\ollama\lib\ollama\cuda_v12.

<!-- gh-comment-id:3101914152 --> @rick-github commented on GitHub (Jul 22, 2025): ``` load_backend: loaded CUDA backend from C:\ollama\lib\ollama\ggml-cuda.dll load_backend: loaded CUDA backend from C:\ollama\lib\ollama\cuda_v12\ggml-cuda.dll ``` #11211 Delete `C:\ollama\lib\ollama\cuda_v12`.
GiteaMirror commented 2026-04-12 19:40:44 -05:00
Author
Owner
Copy Link

@DanoPTT commented on GitHub (Jul 22, 2025):

I delete directory C:\ollama\lib\ollama\cuda_v12 but then next error appears when I try to run gemma model.
ollama run gemma3:12b
Error: llama runner process has terminated: error:fault

<!-- gh-comment-id:3102193485 --> @DanoPTT commented on GitHub (Jul 22, 2025): I delete directory C:\ollama\lib\ollama\cuda_v12 but then next error appears when I try to run gemma model. ollama run gemma3:12b Error: llama runner process has terminated: error:fault
GiteaMirror commented 2026-04-12 19:40:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2025):

Logs?

<!-- gh-comment-id:3102209152 --> @rick-github commented on GitHub (Jul 22, 2025): Logs?
GiteaMirror commented 2026-04-12 19:40:44 -05:00
Author
Owner
Copy Link

@DanoPTT commented on GitHub (Jul 22, 2025):

Now it runs, but on CPU, not GPU, so is very slow.
Here is log:
time=2025-07-22T14:54:25.043+02:00 level=INFO source=routes.go:1235 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://0.0.0.0:11434 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:\ollama\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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=2025-07-22T14:54:25.047+02:00 level=INFO source=images.go:476 msg="total blobs: 12"
time=2025-07-22T14:54:25.047+02:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0"
time=2025-07-22T14:54:25.048+02:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)"
time=2025-07-22T14:54:25.048+02:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-07-22T14:54:25.048+02:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-07-22T14:54:25.048+02:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12
time=2025-07-22T14:54:25.200+02:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" overhead="890.0 MiB"
time=2025-07-22T14:54:25.201+02:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" total="15.9 GiB" available="14.7 GiB"
[GIN] 2025/07/22 - 14:54:25 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/07/22 - 14:54:25 | 200 | 133.1068ms | 127.0.0.1 | POST "/api/show"
time=2025-07-22T14:54:25.723+02:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de gpu=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a parallel=2 available=15804137472 required="11.0 GiB"
time=2025-07-22T14:54:25.753+02:00 level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="16.6 GiB" free_swap="11.9 GiB"
time=2025-07-22T14:54:25.756+02:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[14.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.0 GiB" memory.required.partial="11.0 GiB" memory.required.kv="1.3 GiB" memory.required.allocations="[11.0 GiB]" memory.weights.total="6.8 GiB" memory.weights.repeating="6.0 GiB" memory.weights.nonrepeating="787.5 MiB" memory.graph.full="519.5 MiB" memory.graph.partial="1.3 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
time=2025-07-22T14:54:25.843+02:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\ollama\ollama.exe runner --ollama-engine --model C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de --ctx-size 8192 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 2 --port 52252"
time=2025-07-22T14:54:25.849+02:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-07-22T14:54:25.849+02:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-07-22T14:54:25.850+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
time=2025-07-22T14:54:25.889+02:00 level=INFO source=runner.go:925 msg="starting ollama engine"
time=2025-07-22T14:54:25.892+02:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:52252"
time=2025-07-22T14:54:25.954+02:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=37
time=2025-07-22T14:54:25.963+02:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(clang)
time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:359 msg="offloading 48 repeating layers to GPU"
time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:375 msg="offloaded 0/49 layers to GPU"
time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="8.3 GiB"
time=2025-07-22T14:54:26.103+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
time=2025-07-22T14:54:26.177+02:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
time=2025-07-22T14:54:26.386+02:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
time=2025-07-22T14:54:31.652+02:00 level=INFO source=server.go:637 msg="llama runner started in 5.80 seconds"
[GIN] 2025/07/22 - 14:54:31 | 200 | 6.1639797s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/07/22 - 14:55:03 | 200 | 21.5042831s | 127.0.0.1 | POST "/api/chat"

<!-- gh-comment-id:3102620204 --> @DanoPTT commented on GitHub (Jul 22, 2025): Now it runs, but on CPU, not GPU, so is very slow. Here is log: time=2025-07-22T14:54:25.043+02:00 level=INFO source=routes.go:1235 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://0.0.0.0:11434 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:\\ollama\\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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=2025-07-22T14:54:25.047+02:00 level=INFO source=images.go:476 msg="total blobs: 12" time=2025-07-22T14:54:25.047+02:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0" time=2025-07-22T14:54:25.048+02:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)" time=2025-07-22T14:54:25.048+02:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-07-22T14:54:25.048+02:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-07-22T14:54:25.048+02:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12 time=2025-07-22T14:54:25.200+02:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" overhead="890.0 MiB" time=2025-07-22T14:54:25.201+02:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" total="15.9 GiB" available="14.7 GiB" [GIN] 2025/07/22 - 14:54:25 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/07/22 - 14:54:25 | 200 | 133.1068ms | 127.0.0.1 | POST "/api/show" time=2025-07-22T14:54:25.723+02:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=C:\ollama\Models\blobs\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de gpu=GPU-29d9387c-984f-b168-0ba2-2b7477a4fc3a parallel=2 available=15804137472 required="11.0 GiB" time=2025-07-22T14:54:25.753+02:00 level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="16.6 GiB" free_swap="11.9 GiB" time=2025-07-22T14:54:25.756+02:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[14.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.0 GiB" memory.required.partial="11.0 GiB" memory.required.kv="1.3 GiB" memory.required.allocations="[11.0 GiB]" memory.weights.total="6.8 GiB" memory.weights.repeating="6.0 GiB" memory.weights.nonrepeating="787.5 MiB" memory.graph.full="519.5 MiB" memory.graph.partial="1.3 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" time=2025-07-22T14:54:25.843+02:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\ollama\\ollama.exe runner --ollama-engine --model C:\\ollama\\Models\\blobs\\sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de --ctx-size 8192 --batch-size 512 --n-gpu-layers 49 --threads 6 --no-mmap --parallel 2 --port 52252" time=2025-07-22T14:54:25.849+02:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-07-22T14:54:25.849+02:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-07-22T14:54:25.850+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" time=2025-07-22T14:54:25.889+02:00 level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-07-22T14:54:25.892+02:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:52252" time=2025-07-22T14:54:25.954+02:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=37 time=2025-07-22T14:54:25.963+02:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(clang) time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:359 msg="offloading 48 repeating layers to GPU" time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:375 msg="offloaded 0/49 layers to GPU" time=2025-07-22T14:54:25.967+02:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="8.3 GiB" time=2025-07-22T14:54:26.103+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" time=2025-07-22T14:54:26.177+02:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" time=2025-07-22T14:54:26.386+02:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" time=2025-07-22T14:54:31.652+02:00 level=INFO source=server.go:637 msg="llama runner started in 5.80 seconds" [GIN] 2025/07/22 - 14:54:31 | 200 | 6.1639797s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/07/22 - 14:55:03 | 200 | 21.5042831s | 127.0.0.1 | POST "/api/chat"
GiteaMirror commented 2026-04-12 19:40:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2025):

time=2025-07-22T14:54:25.963+02:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(clang)

No CPU or GPU backends loaded. I suggest reinstalling.

<!-- gh-comment-id:3102656670 --> @rick-github commented on GitHub (Jul 22, 2025): ``` time=2025-07-22T14:54:25.963+02:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(clang) ``` No CPU or GPU backends loaded. I suggest reinstalling.
GiteaMirror commented 2026-04-12 19:40:45 -05:00
Author
Owner
Copy Link

@DanoPTT commented on GitHub (Jul 22, 2025):

Finally, I found solution.
I uninstall ollama (keeping models), than install latest version of ollama, and now is OK. Now Gemma runs in GPU.

<!-- gh-comment-id:3102778099 --> @DanoPTT commented on GitHub (Jul 22, 2025): Finally, I found solution. I uninstall ollama (keeping models), than install latest version of ollama, and now is OK. Now Gemma runs in GPU.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#7590
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?