github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11677] ollama docker - gpt-oss:20b - ggml-cpu/ops.cpp:965: fatal error #69783

New Issue
Closed
opened 2026-05-04 19:16:38 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 19:16:38 -05:00
Owner
Copy Link

Originally created by @McBane87 on GitHub (Aug 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11677

What is the issue?

Getting the following error when trying to chat with gpt-oss:20b on ollama docker image

Relevant log output

time=2025-08-05T18:03:46.068Z level=INFO source=routes.go:1297 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:8192 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2h0m0s OLLAMA_KV_CACHE_TYPE:q8_0 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:16 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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:]"
time=2025-08-05T18:03:46.071Z level=INFO source=images.go:477 msg="total blobs: 47"
time=2025-08-05T18:03:46.071Z level=INFO source=images.go:484 msg="total unused blobs removed: 0"
time=2025-08-05T18:03:46.072Z level=INFO source=routes.go:1350 msg="Listening on [::]:11434 (version 0.11.0)"
time=2025-08-05T18:03:46.072Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-05T18:03:46.165Z level=INFO source=types.go:130 msg="inference compute" id=GPU-fcb13367-7dce-0a35-3d7a-29fa2f322303 library=cuda variant=v12 compute=8.6 driver=12.4 name="NVIDIA GeForce RTX 3060" total="11.8 GiB" available="11.6 GiB"
time=2025-08-05T18:03:58.330Z level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="28.4 GiB" free_swap="0 B"
time=2025-08-05T18:03:58.397Z level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=19 layers.split="" memory.available="[11.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="14.8 GiB" memory.required.partial="11.5 GiB" memory.required.kv="150.0 MiB" memory.required.allocations="[11.5 GiB]" memory.weights.total="11.7 GiB" memory.weights.repeating="10.7 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="1.0 GiB" memory.graph.partial="2.0 GiB"
time=2025-08-05T18:03:58.398Z level=INFO source=server.go:218 msg="enabling flash attention"
time=2025-08-05T18:03:58.446Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 8192 --batch-size 512 --n-gpu-layers 19 --threads 8 --flash-attn --kv-cache-type q8_0 --parallel 1 --port 38669"
time=2025-08-05T18:03:58.446Z level=INFO source=sched.go:481 msg="loaded runners" count=1
time=2025-08-05T18:03:58.446Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-08-05T18:03:58.447Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
time=2025-08-05T18:03:58.458Z level=INFO source=runner.go:925 msg="starting ollama engine"
time=2025-08-05T18:03:58.458Z level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:38669"
time=2025-08-05T18:03:58.511Z level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30
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 3060, compute capability 8.6, VMM: yes
load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so
time=2025-08-05T18:03:58.578Z 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.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(gcc)
time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:367 msg="offloading 19 repeating layers to GPU"
time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:371 msg="offloading output layer to CPU"
time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:378 msg="offloaded 19/25 layers to GPU"
time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:381 msg="model weights" buffer=CPU size="4.4 GiB"
time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:381 msg="model weights" buffer=CUDA0 size="8.4 GiB"
time=2025-08-05T18:03:58.654Z level=INFO source=ggml.go:672 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="2.1 GiB"
time=2025-08-05T18:03:58.654Z level=INFO source=ggml.go:672 msg="compute graph" backend=CPU buffer_type=CPU size="2.0 GiB"
time=2025-08-05T18:03:58.703Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
time=2025-08-05T18:04:00.460Z level=INFO source=server.go:637 msg="llama runner started in 2.01 seconds"
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
//ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error
SIGSEGV: segmentation violation
PC=0x73aa55c24fb7 m=12 sigcode=1 addr=0x204a03fa8
signal arrived during cgo execution

goroutine 37 gp=0xc0001d1c00 m=12 mp=0xc000101008 [syscall]:
runtime.cgocall(0x571fcc14f180, 0xc001927a58)
        runtime/cgocall.go:167 +0x4b fp=0xc001927a30 sp=0xc0019279f8 pc=0x571fcb4828cb
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x73aa69011170, 0x73a5400045d0)
        _cgo_gotypes.go:886 +0x4a fp=0xc001927a58 sp=0xc001927a30 pc=0x571fcb8bc4ea
github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute.func1(...)
        github.com/ollama/ollama/ml/backend/ggml/ggml.go:631
github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute(0xc00182c000, {0xc000114510, 0x1, 0x0?})
        github.com/ollama/ollama/ml/backend/ggml/ggml.go:631 +0x9d fp=0xc001927b00 sp=0xc001927a58 pc=0x571fcb8c79fd
github.com/ollama/ollama/model.Forward({0x571fcc803d30, 0xc00182c000}, {0x571fcc7fa550, 0xc0000d96b0}, {0xc001a7a400, 0x49, 0x80}, {{0x571fcc80e988, 0xc0018587e0}, {0x0, ...}, ...})
        github.com/ollama/ollama/model/model.go:305 +0x2a7 fp=0xc001927be8 sp=0xc001927b00 pc=0x571fcb8d59c7
github.com/ollama/ollama/runner/ollamarunner.(*Server).processBatch(0xc0005c39e0)
        github.com/ollama/ollama/runner/ollamarunner/runner.go:480 +0x4c5 fp=0xc001927f98 sp=0xc001927be8 pc=0x571fcb976905
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0005c39e0, {0x571fcc7fba30, 0xc00013e2d0})
        github.com/ollama/ollama/runner/ollamarunner/runner.go:362 +0x4e fp=0xc001927fb8 sp=0xc001927f98 pc=0x571fcb9763ee
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap2()
        github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0x28 fp=0xc001927fe0 sp=0xc001927fb8 pc=0x571fcb97bb48
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc001927fe8 sp=0xc001927fe0 pc=0x571fcb48d481
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
        github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74

goroutine 1 gp=0xc000002380 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc0004bb650 sp=0xc0004bb630 pc=0x571fcb485d4e
runtime.netpollblock(0xc0004bb6a0?, 0xcb41eb46?, 0x1f?)
        runtime/netpoll.go:575 +0xf7 fp=0xc0004bb688 sp=0xc0004bb650 pc=0x571fcb44a837
internal/poll.runtime_pollWait(0x73aabf05ceb0, 0x72)
        runtime/netpoll.go:351 +0x85 fp=0xc0004bb6a8 sp=0xc0004bb688 pc=0x571fcb484f65
internal/poll.(*pollDesc).wait(0xc0005ab900?, 0x900000036?, 0x0)
        internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0004bb6d0 sp=0xc0004bb6a8 pc=0x571fcb50c3a7
internal/poll.(*pollDesc).waitRead(...)
        internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc0005ab900)
        internal/poll/fd_unix.go:620 +0x295 fp=0xc0004bb778 sp=0xc0004bb6d0 pc=0x571fcb511775
net.(*netFD).accept(0xc0005ab900)
        net/fd_unix.go:172 +0x29 fp=0xc0004bb830 sp=0xc0004bb778 pc=0x571fcb583d89
net.(*TCPListener).accept(0xc00013a100)
        net/tcpsock_posix.go:159 +0x1b fp=0xc0004bb880 sp=0xc0004bb830 pc=0x571fcb59973b
net.(*TCPListener).Accept(0xc00013a100)
        net/tcpsock.go:380 +0x30 fp=0xc0004bb8b0 sp=0xc0004bb880 pc=0x571fcb5985f0
net/http.(*onceCloseListener).Accept(0xc000122090?)
        <autogenerated>:1 +0x24 fp=0xc0004bb8c8 sp=0xc0004bb8b0 pc=0x571fcb7afd44
net/http.(*Server).Serve(0xc0000f4000, {0x571fcc7f9588, 0xc00013a100})
        net/http/server.go:3424 +0x30c fp=0xc0004bb9f8 sp=0xc0004bb8c8 pc=0x571fcb78760c
github.com/ollama/ollama/runner/ollamarunner.Execute({0xc000034170, 0x11, 0x11})
        github.com/ollama/ollama/runner/ollamarunner/runner.go:984 +0xe09 fp=0xc0004bbd08 sp=0xc0004bb9f8 pc=0x571fcb97b8a9
github.com/ollama/ollama/runner.Execute({0xc000034150?, 0x0?, 0x0?})
        github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc0004bbd30 sp=0xc0004bbd08 pc=0x571fcb97c1a9
github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f3300?, {0x571fcc33c07b?, 0x4?, 0x571fcc33c07f?})
        github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc0004bbd58 sp=0xc0004bbd30 pc=0x571fcc0e10e5
github.com/spf13/cobra.(*Command).execute(0xc000166f08, {0xc0005c37a0, 0x12, 0x12})
        github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0004bbe78 sp=0xc0004bbd58 pc=0x571fcb5fd3dc
github.com/spf13/cobra.(*Command).ExecuteC(0xc00049ef08)
        github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0004bbf30 sp=0xc0004bbe78 pc=0x571fcb5fdc25
github.com/spf13/cobra.(*Command).Execute(...)
        github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
        github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
        github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0004bbf50 sp=0xc0004bbf30 pc=0x571fcc0e1bcd
runtime.main()
        runtime/proc.go:283 +0x29d fp=0xc0004bbfe0 sp=0xc0004bbf50 pc=0x571fcb451ebd
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bbfe8 sp=0xc0004bbfe0 pc=0x571fcb48d481

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc000072fa8 sp=0xc000072f88 pc=0x571fcb485d4e
runtime.goparkunlock(...)
        runtime/proc.go:441
runtime.forcegchelper()
        runtime/proc.go:348 +0xb8 fp=0xc000072fe0 sp=0xc000072fa8 pc=0x571fcb4521f8
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x571fcb48d481
created by runtime.init.7 in goroutine 1
        runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc000073780 sp=0xc000073760 pc=0x571fcb485d4e
runtime.goparkunlock(...)
        runtime/proc.go:441
runtime.bgsweep(0xc00007e000)
        runtime/mgcsweep.go:316 +0xdf fp=0xc0000737c8 sp=0xc000073780 pc=0x571fcb43c99f
runtime.gcenable.gowrap1()
        runtime/mgc.go:204 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x571fcb430d85
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x571fcb48d481
created by runtime.gcenable in goroutine 1
        runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x571fcc4fe090?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc000073f78 sp=0xc000073f58 pc=0x571fcb485d4e
runtime.goparkunlock(...)
        runtime/proc.go:441
runtime.(*scavengerState).park(0x571fcd0909a0)
        runtime/mgcscavenge.go:425 +0x49 fp=0xc000073fa8 sp=0xc000073f78 pc=0x571fcb43a3e9
runtime.bgscavenge(0xc00007e000)
        runtime/mgcscavenge.go:658 +0x59 fp=0xc000073fc8 sp=0xc000073fa8 pc=0x571fcb43a979
runtime.gcenable.gowrap2()
        runtime/mgc.go:205 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x571fcb430d25
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x571fcb48d481
created by runtime.gcenable in goroutine 1
        runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000072688?)
        runtime/proc.go:435 +0xce fp=0xc000072630 sp=0xc000072610 pc=0x571fcb485d4e
runtime.runfinq()
        runtime/mfinal.go:196 +0x107 fp=0xc0000727e0 sp=0xc000072630 pc=0x571fcb42fd47
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x571fcb48d481
created by runtime.createfing in goroutine 1
        runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]:
runtime.gopark(0xc00022d680?, 0xc00184a210?, 0x60?, 0x47?, 0x571fcb56a9c8?)
        runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x571fcb485d4e
runtime.chanrecv(0xc0000aa310, 0x0, 0x1)
        runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x571fcb421725
runtime.chanrecv1(0x0?, 0x0?)
        runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x571fcb4212b2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
        runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
        runtime/mgc.go:1799 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x571fcb433f2f
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x571fcb48d481
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
        runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0001d1180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x1362bafbd042e?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x1362bafbd6855?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc00011a738 sp=0xc00011a718 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc00011a7c8 sp=0xc00011a738 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc00011a7e0 sp=0xc00011a7c8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00011a7e8 sp=0xc00011a7e0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0001d1340 m=nil [GC worker (idle)]:
runtime.gopark(0x1362bafbd5135?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc0005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x1362bafbd756b?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc00006ef38 sp=0xc00006ef18 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc00006efc8 sp=0xc00006ef38 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc00006efe0 sp=0xc00006efc8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc000102540 m=nil [GC worker (idle)]:
runtime.gopark(0x1362bb02a8eed?, 0x3?, 0x3?, 0xff?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc00011af38 sp=0xc00011af18 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc00011afc8 sp=0xc00011af38 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc00011afe0 sp=0xc00011afc8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00011afe8 sp=0xc00011afe0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0001d1500 m=nil [GC worker (idle)]:
runtime.gopark(0x1362bafbd087a?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc000075f38 sp=0xc000075f18 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc000075fc8 sp=0xc000075f38 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc000075fe0 sp=0xc000075fc8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000075fe8 sp=0xc000075fe0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 20 gp=0xc000504380 m=nil [GC worker (idle)]:
runtime.gopark(0x1362bb02d001e?, 0x3?, 0xaf?, 0x88?, 0x0?)
        runtime/proc.go:435 +0xce fp=0xc00006f738 sp=0xc00006f718 pc=0x571fcb485d4e
runtime.gcBgMarkWorker(0xc0000ab8f0)
        runtime/mgc.go:1423 +0xe9 fp=0xc00006f7c8 sp=0xc00006f738 pc=0x571fcb433249
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1339 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x571fcb433125
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x571fcb48d481
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1339 +0x105

goroutine 356 gp=0xc0005048c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?)
        runtime/proc.go:435 +0xce fp=0xc0018ef5d8 sp=0xc0018ef5b8 pc=0x571fcb485d4e
runtime.netpollblock(0x571fcb4a90b8?, 0xcb41eb46?, 0x1f?)
        runtime/netpoll.go:575 +0xf7 fp=0xc0018ef610 sp=0xc0018ef5d8 pc=0x571fcb44a837
internal/poll.runtime_pollWait(0x73aabf05cc80, 0x72)
        runtime/netpoll.go:351 +0x85 fp=0xc0018ef630 sp=0xc0018ef610 pc=0x571fcb484f65
internal/poll.(*pollDesc).wait(0xc000126000?, 0xc001856c71?, 0x0)
        internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0018ef658 sp=0xc0018ef630 pc=0x571fcb50c3a7
internal/poll.(*pollDesc).waitRead(...)
        internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc000126000, {0xc001856c71, 0x1, 0x1})
        internal/poll/fd_unix.go:165 +0x27a fp=0xc0018ef6f0 sp=0xc0018ef658 pc=0x571fcb50d69a
net.(*netFD).Read(0xc000126000, {0xc001856c71?, 0xc00187e8d8?, 0xc0018ef770?})
        net/fd_posix.go:55 +0x25 fp=0xc0018ef738 sp=0xc0018ef6f0 pc=0x571fcb581de5
net.(*conn).Read(0xc001b08040, {0xc001856c71?, 0xc00187e5c0?, 0x571fcb7ed060?})
        net/net.go:194 +0x45 fp=0xc0018ef780 sp=0xc0018ef738 pc=0x571fcb5901a5
net/http.(*connReader).backgroundRead(0xc001856c60)
        net/http/server.go:690 +0x37 fp=0xc0018ef7c8 sp=0xc0018ef780 pc=0x571fcb77c017
net/http.(*connReader).startBackgroundRead.gowrap2()
        net/http/server.go:686 +0x25 fp=0xc0018ef7e0 sp=0xc0018ef7c8 pc=0x571fcb77bf45
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0018ef7e8 sp=0xc0018ef7e0 pc=0x571fcb48d481
created by net/http.(*connReader).startBackgroundRead in goroutine 133
        net/http/server.go:686 +0xb6

goroutine 133 gp=0xc000102e00 m=nil [select]:
runtime.gopark(0xc000049a10?, 0x2?, 0x10?, 0x8e?, 0xc000049874?)
        runtime/proc.go:435 +0xce fp=0xc0000496a0 sp=0xc000049680 pc=0x571fcb485d4e
runtime.selectgo(0xc000049a10, 0xc000049870, 0x49?, 0x0, 0x4?, 0x1)
        runtime/select.go:351 +0x837 fp=0xc0000497d8 sp=0xc0000496a0 pc=0x571fcb4643b7
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc0005c39e0, {0x571fcc7f9768, 0xc0019e60e0}, 0xc000140140)
        github.com/ollama/ollama/runner/ollamarunner/runner.go:680 +0xb65 fp=0xc000049ac0 sp=0xc0000497d8 pc=0x571fcb978c45
github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x571fcc7f9768?, 0xc0019e60e0?}, 0xc0004bdb40?)
        <autogenerated>:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x571fcb97c016
net/http.HandlerFunc.ServeHTTP(0xc0000de000?, {0x571fcc7f9768?, 0xc0019e60e0?}, 0xc0004bdb60?)
        net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x571fcb783c49
net/http.(*ServeMux).ServeHTTP(0x571fcb42a265?, {0x571fcc7f9768, 0xc0019e60e0}, 0xc000140140)
        net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x571fcb785b44
net/http.serverHandler.ServeHTTP({0x571fcc7f5db0?}, {0x571fcc7f9768?, 0xc0019e60e0?}, 0x1?)
        net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x571fcb7a35ce
net/http.(*conn).serve(0xc000122090, {0x571fcc7fb9f8, 0xc000272e40})
        net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x571fcb782145
net/http.(*Server).Serve.gowrap3()
        net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x571fcb787a08
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x571fcb48d481
created by net/http.(*Server).Serve in goroutine 1
        net/http/server.go:3454 +0x485

rax    0x204a03fa8
rbx    0x73aa687b1e90
rcx    0xfea
rdx    0x73aa686490d0
rdi    0x73aa686490e0
rsi    0x0
rbp    0x73a9b1ffe2c0
rsp    0x73a9b1ffe2a0
r8     0x1
r9     0x73aa573f7020
r10    0x0
r11    0x246
r12    0x571fe7a85650
r13    0x73aa686490e0
r14    0x0
r15    0x73aa68002eb0
rip    0x73aa55c24fb7
rflags 0x10297
cs     0x33
fs     0x0
gs     0x0
time=2025-08-05T18:04:01.295Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:38669/completion\": EOF"
[GIN] 2025/08/05 - 18:04:01 | 200 |  3.430154968s |      172.17.0.1 | POST     "/api/chat"

OS

  • Ubuntu 24.04 with docker
    • ollama:latest (sha256:99f0642fc78d5d70f7518129f0c0680f8366cf1b0b28ccf05b3db6123002ad70)

GPU

NVIDIA RTX 3060 12GB

CPU

AMD Ryzen 7900

Ollama version

0.11.0

Originally created by @McBane87 on GitHub (Aug 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11677 ### What is the issue? Getting the following error when trying to chat with gpt-oss:20b on ollama docker image ### Relevant log output ```shell time=2025-08-05T18:03:46.068Z level=INFO source=routes.go:1297 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:8192 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2h0m0s OLLAMA_KV_CACHE_TYPE:q8_0 OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:16 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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:]" time=2025-08-05T18:03:46.071Z level=INFO source=images.go:477 msg="total blobs: 47" time=2025-08-05T18:03:46.071Z level=INFO source=images.go:484 msg="total unused blobs removed: 0" time=2025-08-05T18:03:46.072Z level=INFO source=routes.go:1350 msg="Listening on [::]:11434 (version 0.11.0)" time=2025-08-05T18:03:46.072Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-08-05T18:03:46.165Z level=INFO source=types.go:130 msg="inference compute" id=GPU-fcb13367-7dce-0a35-3d7a-29fa2f322303 library=cuda variant=v12 compute=8.6 driver=12.4 name="NVIDIA GeForce RTX 3060" total="11.8 GiB" available="11.6 GiB" time=2025-08-05T18:03:58.330Z level=INFO source=server.go:135 msg="system memory" total="31.3 GiB" free="28.4 GiB" free_swap="0 B" time=2025-08-05T18:03:58.397Z level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=19 layers.split="" memory.available="[11.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="14.8 GiB" memory.required.partial="11.5 GiB" memory.required.kv="150.0 MiB" memory.required.allocations="[11.5 GiB]" memory.weights.total="11.7 GiB" memory.weights.repeating="10.7 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="1.0 GiB" memory.graph.partial="2.0 GiB" time=2025-08-05T18:03:58.398Z level=INFO source=server.go:218 msg="enabling flash attention" time=2025-08-05T18:03:58.446Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 --ctx-size 8192 --batch-size 512 --n-gpu-layers 19 --threads 8 --flash-attn --kv-cache-type q8_0 --parallel 1 --port 38669" time=2025-08-05T18:03:58.446Z level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-08-05T18:03:58.446Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-05T18:03:58.447Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-08-05T18:03:58.458Z level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-08-05T18:03:58.458Z level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:38669" time=2025-08-05T18:03:58.511Z level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=315 num_key_values=30 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 3060, compute capability 8.6, VMM: yes load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so time=2025-08-05T18:03:58.578Z 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.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(gcc) time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:367 msg="offloading 19 repeating layers to GPU" time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:371 msg="offloading output layer to CPU" time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:378 msg="offloaded 19/25 layers to GPU" time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:381 msg="model weights" buffer=CPU size="4.4 GiB" time=2025-08-05T18:03:58.630Z level=INFO source=ggml.go:381 msg="model weights" buffer=CUDA0 size="8.4 GiB" time=2025-08-05T18:03:58.654Z level=INFO source=ggml.go:672 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="2.1 GiB" time=2025-08-05T18:03:58.654Z level=INFO source=ggml.go:672 msg="compute graph" backend=CPU buffer_type=CPU size="2.0 GiB" time=2025-08-05T18:03:58.703Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" time=2025-08-05T18:04:00.460Z level=INFO source=server.go:637 msg="llama runner started in 2.01 seconds" //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error //ml/backend/ggml/ggml/src/ggml-cpu/ops.cpp:965: fatal error SIGSEGV: segmentation violation PC=0x73aa55c24fb7 m=12 sigcode=1 addr=0x204a03fa8 signal arrived during cgo execution goroutine 37 gp=0xc0001d1c00 m=12 mp=0xc000101008 [syscall]: runtime.cgocall(0x571fcc14f180, 0xc001927a58) runtime/cgocall.go:167 +0x4b fp=0xc001927a30 sp=0xc0019279f8 pc=0x571fcb4828cb github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x73aa69011170, 0x73a5400045d0) _cgo_gotypes.go:886 +0x4a fp=0xc001927a58 sp=0xc001927a30 pc=0x571fcb8bc4ea github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute.func1(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:631 github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute(0xc00182c000, {0xc000114510, 0x1, 0x0?}) github.com/ollama/ollama/ml/backend/ggml/ggml.go:631 +0x9d fp=0xc001927b00 sp=0xc001927a58 pc=0x571fcb8c79fd github.com/ollama/ollama/model.Forward({0x571fcc803d30, 0xc00182c000}, {0x571fcc7fa550, 0xc0000d96b0}, {0xc001a7a400, 0x49, 0x80}, {{0x571fcc80e988, 0xc0018587e0}, {0x0, ...}, ...}) github.com/ollama/ollama/model/model.go:305 +0x2a7 fp=0xc001927be8 sp=0xc001927b00 pc=0x571fcb8d59c7 github.com/ollama/ollama/runner/ollamarunner.(*Server).processBatch(0xc0005c39e0) github.com/ollama/ollama/runner/ollamarunner/runner.go:480 +0x4c5 fp=0xc001927f98 sp=0xc001927be8 pc=0x571fcb976905 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0005c39e0, {0x571fcc7fba30, 0xc00013e2d0}) github.com/ollama/ollama/runner/ollamarunner/runner.go:362 +0x4e fp=0xc001927fb8 sp=0xc001927f98 pc=0x571fcb9763ee github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap2() github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0x28 fp=0xc001927fe0 sp=0xc001927fb8 pc=0x571fcb97bb48 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc001927fe8 sp=0xc001927fe0 pc=0x571fcb48d481 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74 goroutine 1 gp=0xc000002380 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0004bb650 sp=0xc0004bb630 pc=0x571fcb485d4e runtime.netpollblock(0xc0004bb6a0?, 0xcb41eb46?, 0x1f?) runtime/netpoll.go:575 +0xf7 fp=0xc0004bb688 sp=0xc0004bb650 pc=0x571fcb44a837 internal/poll.runtime_pollWait(0x73aabf05ceb0, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0004bb6a8 sp=0xc0004bb688 pc=0x571fcb484f65 internal/poll.(*pollDesc).wait(0xc0005ab900?, 0x900000036?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0004bb6d0 sp=0xc0004bb6a8 pc=0x571fcb50c3a7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0xc0005ab900) internal/poll/fd_unix.go:620 +0x295 fp=0xc0004bb778 sp=0xc0004bb6d0 pc=0x571fcb511775 net.(*netFD).accept(0xc0005ab900) net/fd_unix.go:172 +0x29 fp=0xc0004bb830 sp=0xc0004bb778 pc=0x571fcb583d89 net.(*TCPListener).accept(0xc00013a100) net/tcpsock_posix.go:159 +0x1b fp=0xc0004bb880 sp=0xc0004bb830 pc=0x571fcb59973b net.(*TCPListener).Accept(0xc00013a100) net/tcpsock.go:380 +0x30 fp=0xc0004bb8b0 sp=0xc0004bb880 pc=0x571fcb5985f0 net/http.(*onceCloseListener).Accept(0xc000122090?) <autogenerated>:1 +0x24 fp=0xc0004bb8c8 sp=0xc0004bb8b0 pc=0x571fcb7afd44 net/http.(*Server).Serve(0xc0000f4000, {0x571fcc7f9588, 0xc00013a100}) net/http/server.go:3424 +0x30c fp=0xc0004bb9f8 sp=0xc0004bb8c8 pc=0x571fcb78760c github.com/ollama/ollama/runner/ollamarunner.Execute({0xc000034170, 0x11, 0x11}) github.com/ollama/ollama/runner/ollamarunner/runner.go:984 +0xe09 fp=0xc0004bbd08 sp=0xc0004bb9f8 pc=0x571fcb97b8a9 github.com/ollama/ollama/runner.Execute({0xc000034150?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc0004bbd30 sp=0xc0004bbd08 pc=0x571fcb97c1a9 github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f3300?, {0x571fcc33c07b?, 0x4?, 0x571fcc33c07f?}) github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc0004bbd58 sp=0xc0004bbd30 pc=0x571fcc0e10e5 github.com/spf13/cobra.(*Command).execute(0xc000166f08, {0xc0005c37a0, 0x12, 0x12}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0004bbe78 sp=0xc0004bbd58 pc=0x571fcb5fd3dc github.com/spf13/cobra.(*Command).ExecuteC(0xc00049ef08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0004bbf30 sp=0xc0004bbe78 pc=0x571fcb5fdc25 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0004bbf50 sp=0xc0004bbf30 pc=0x571fcc0e1bcd runtime.main() runtime/proc.go:283 +0x29d fp=0xc0004bbfe0 sp=0xc0004bbf50 pc=0x571fcb451ebd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bbfe8 sp=0xc0004bbfe0 pc=0x571fcb48d481 goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000072fa8 sp=0xc000072f88 pc=0x571fcb485d4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc000072fe0 sp=0xc000072fa8 pc=0x571fcb4521f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x571fcb48d481 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000073780 sp=0xc000073760 pc=0x571fcb485d4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc00007e000) runtime/mgcsweep.go:316 +0xdf fp=0xc0000737c8 sp=0xc000073780 pc=0x571fcb43c99f runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x571fcb430d85 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x571fcb48d481 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x571fcc4fe090?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000073f78 sp=0xc000073f58 pc=0x571fcb485d4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x571fcd0909a0) runtime/mgcscavenge.go:425 +0x49 fp=0xc000073fa8 sp=0xc000073f78 pc=0x571fcb43a3e9 runtime.bgscavenge(0xc00007e000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000073fc8 sp=0xc000073fa8 pc=0x571fcb43a979 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x571fcb430d25 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x571fcb48d481 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000072688?) runtime/proc.go:435 +0xce fp=0xc000072630 sp=0xc000072610 pc=0x571fcb485d4e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc0000727e0 sp=0xc000072630 pc=0x571fcb42fd47 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x571fcb48d481 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]: runtime.gopark(0xc00022d680?, 0xc00184a210?, 0x60?, 0x47?, 0x571fcb56a9c8?) runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x571fcb485d4e runtime.chanrecv(0xc0000aa310, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x571fcb421725 runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x571fcb4212b2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x571fcb433f2f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x571fcb48d481 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0001d1180 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc000504000 m=nil [GC worker (idle)]: runtime.gopark(0x1362bafbd042e?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc000102380 m=nil [GC worker (idle)]: runtime.gopark(0x1362bafbd6855?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011a738 sp=0xc00011a718 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc00011a7c8 sp=0xc00011a738 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011a7e0 sp=0xc00011a7c8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011a7e8 sp=0xc00011a7e0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0001d1340 m=nil [GC worker (idle)]: runtime.gopark(0x1362bafbd5135?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc0005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x1362bafbd756b?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006ef38 sp=0xc00006ef18 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc00006efc8 sp=0xc00006ef38 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006efe0 sp=0xc00006efc8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc000102540 m=nil [GC worker (idle)]: runtime.gopark(0x1362bb02a8eed?, 0x3?, 0x3?, 0xff?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011af38 sp=0xc00011af18 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc00011afc8 sp=0xc00011af38 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011afe0 sp=0xc00011afc8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011afe8 sp=0xc00011afe0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0001d1500 m=nil [GC worker (idle)]: runtime.gopark(0x1362bafbd087a?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000075f38 sp=0xc000075f18 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc000075fc8 sp=0xc000075f38 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000075fe0 sp=0xc000075fc8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000075fe8 sp=0xc000075fe0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 20 gp=0xc000504380 m=nil [GC worker (idle)]: runtime.gopark(0x1362bb02d001e?, 0x3?, 0xaf?, 0x88?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006f738 sp=0xc00006f718 pc=0x571fcb485d4e runtime.gcBgMarkWorker(0xc0000ab8f0) runtime/mgc.go:1423 +0xe9 fp=0xc00006f7c8 sp=0xc00006f738 pc=0x571fcb433249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x571fcb433125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x571fcb48d481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 356 gp=0xc0005048c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?) runtime/proc.go:435 +0xce fp=0xc0018ef5d8 sp=0xc0018ef5b8 pc=0x571fcb485d4e runtime.netpollblock(0x571fcb4a90b8?, 0xcb41eb46?, 0x1f?) runtime/netpoll.go:575 +0xf7 fp=0xc0018ef610 sp=0xc0018ef5d8 pc=0x571fcb44a837 internal/poll.runtime_pollWait(0x73aabf05cc80, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0018ef630 sp=0xc0018ef610 pc=0x571fcb484f65 internal/poll.(*pollDesc).wait(0xc000126000?, 0xc001856c71?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0018ef658 sp=0xc0018ef630 pc=0x571fcb50c3a7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0xc000126000, {0xc001856c71, 0x1, 0x1}) internal/poll/fd_unix.go:165 +0x27a fp=0xc0018ef6f0 sp=0xc0018ef658 pc=0x571fcb50d69a net.(*netFD).Read(0xc000126000, {0xc001856c71?, 0xc00187e8d8?, 0xc0018ef770?}) net/fd_posix.go:55 +0x25 fp=0xc0018ef738 sp=0xc0018ef6f0 pc=0x571fcb581de5 net.(*conn).Read(0xc001b08040, {0xc001856c71?, 0xc00187e5c0?, 0x571fcb7ed060?}) net/net.go:194 +0x45 fp=0xc0018ef780 sp=0xc0018ef738 pc=0x571fcb5901a5 net/http.(*connReader).backgroundRead(0xc001856c60) net/http/server.go:690 +0x37 fp=0xc0018ef7c8 sp=0xc0018ef780 pc=0x571fcb77c017 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x25 fp=0xc0018ef7e0 sp=0xc0018ef7c8 pc=0x571fcb77bf45 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0018ef7e8 sp=0xc0018ef7e0 pc=0x571fcb48d481 created by net/http.(*connReader).startBackgroundRead in goroutine 133 net/http/server.go:686 +0xb6 goroutine 133 gp=0xc000102e00 m=nil [select]: runtime.gopark(0xc000049a10?, 0x2?, 0x10?, 0x8e?, 0xc000049874?) runtime/proc.go:435 +0xce fp=0xc0000496a0 sp=0xc000049680 pc=0x571fcb485d4e runtime.selectgo(0xc000049a10, 0xc000049870, 0x49?, 0x0, 0x4?, 0x1) runtime/select.go:351 +0x837 fp=0xc0000497d8 sp=0xc0000496a0 pc=0x571fcb4643b7 github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc0005c39e0, {0x571fcc7f9768, 0xc0019e60e0}, 0xc000140140) github.com/ollama/ollama/runner/ollamarunner/runner.go:680 +0xb65 fp=0xc000049ac0 sp=0xc0000497d8 pc=0x571fcb978c45 github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x571fcc7f9768?, 0xc0019e60e0?}, 0xc0004bdb40?) <autogenerated>:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x571fcb97c016 net/http.HandlerFunc.ServeHTTP(0xc0000de000?, {0x571fcc7f9768?, 0xc0019e60e0?}, 0xc0004bdb60?) net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x571fcb783c49 net/http.(*ServeMux).ServeHTTP(0x571fcb42a265?, {0x571fcc7f9768, 0xc0019e60e0}, 0xc000140140) net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x571fcb785b44 net/http.serverHandler.ServeHTTP({0x571fcc7f5db0?}, {0x571fcc7f9768?, 0xc0019e60e0?}, 0x1?) net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x571fcb7a35ce net/http.(*conn).serve(0xc000122090, {0x571fcc7fb9f8, 0xc000272e40}) net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x571fcb782145 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x571fcb787a08 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x571fcb48d481 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 rax 0x204a03fa8 rbx 0x73aa687b1e90 rcx 0xfea rdx 0x73aa686490d0 rdi 0x73aa686490e0 rsi 0x0 rbp 0x73a9b1ffe2c0 rsp 0x73a9b1ffe2a0 r8 0x1 r9 0x73aa573f7020 r10 0x0 r11 0x246 r12 0x571fe7a85650 r13 0x73aa686490e0 r14 0x0 r15 0x73aa68002eb0 rip 0x73aa55c24fb7 rflags 0x10297 cs 0x33 fs 0x0 gs 0x0 time=2025-08-05T18:04:01.295Z level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:38669/completion\": EOF" [GIN] 2025/08/05 - 18:04:01 | 200 | 3.430154968s | 172.17.0.1 | POST "/api/chat" ``` ### OS - Ubuntu 24.04 with docker - ollama:latest (sha256:99f0642fc78d5d70f7518129f0c0680f8366cf1b0b28ccf05b3db6123002ad70) ### GPU NVIDIA RTX 3060 12GB ### CPU AMD Ryzen 7900 ### Ollama version 0.11.0
GiteaMirror added the bug label 2026-05-04 19:16:38 -05:00
GiteaMirror commented 2026-05-04 19:16:45 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Aug 5, 2025):

This might be related to KV cache quantization, you can try using the default setting and seeing if that helps.

<!-- gh-comment-id:3156222995 --> @jessegross commented on GitHub (Aug 5, 2025): This might be related to KV cache quantization, you can try using the default setting and seeing if that helps.
GiteaMirror commented 2026-05-04 19:16:47 -05:00
Author
Owner
Copy Link

@McBane87 commented on GitHub (Aug 5, 2025):

Yes, using default KV Cache prevents the error.

<!-- gh-comment-id:3156238020 --> @McBane87 commented on GitHub (Aug 5, 2025): Yes, using default KV Cache prevents the error.
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#69783
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?