github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 14:13:13 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14325] consistent SIGBUS when running gpt-oss:20b via Vulkan+Nouvau on RTX3090 #55833

New Issue
Open
opened 2026-04-29 09:47:20 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 09:47:20 -05:00
Owner
Copy Link

Originally created by @morgwai on GitHub (Feb 19, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14325

What is the issue?

I wanted to test the perf when using Vulkan+Nouveau comparing to CUDA, so I ran llm_benchmark, which loads and prompts various models and measures the output. When gpt-oss:20b was loaded and prompt Summarize the key differences between classical and operant conditioning in psychology issued, the runner crashed due to SIGBUS. I retried 2 times and it happens consistently. It works ok via CUDA. Also when using Vulkan + Nouveau + gpt-oss:20b and issuing the same prompt manually, it works fine, so it must be a very specific chain of events that triggers the bug.

OS: Debian-13
kernel: 6.18.5+deb13-amd64
firmware-nvidia-graphics: 20251021-1~bpo13+1 (contains GSP 570.144)
Host: TUXEDO InfinityBook Pro 14 - Gen10 - AMD (HX370 APU), 128GB RAM
GPU: RTX 3090
server cmd: OLLAMA_VULKAN=1 GGML_VK_VISIBLE_DEVICES=0 ollama serve (full log: ollama-sigbus.log)
llm_benchmark version: 0.5.1
llm_benchmark cmd: llm_benchmark run (output: llm-benchmark.log)

Relevant log output

time=2026-02-19T19:40:14.235+01:00 level=INFO source=routes.go:1636 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/home/morgwai/.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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2026-02-19T19:40:14.238+01:00 level=INFO source=images.go:473 msg="total blobs: 67"
time=2026-02-19T19:40:14.238+01:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
time=2026-02-19T19:40:14.239+01:00 level=INFO source=routes.go:1689 msg="Listening on 127.0.0.1:11434 (version 0.15.6)"
time=2026-02-19T19:40:14.239+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-02-19T19:40:14.239+01:00 level=WARN source=runner.go:485 msg="user overrode visible devices" GGML_VK_VISIBLE_DEVICES=0
time=2026-02-19T19:40:14.239+01:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again"
time=2026-02-19T19:40:14.240+01:00 level=INFO source=server.go:431 msg="starting runner" cmd="/var/opt/ollama-0.15.6/bin/ollama runner --ollama-engine --port 37889"
time=2026-02-19T19:40:14.266+01:00 level=INFO source=server.go:431 msg="starting runner" cmd="/var/opt/ollama-0.15.6/bin/ollama runner --ollama-engine --port 34073"
time=2026-02-19T19:40:14.283+01:00 level=INFO source=server.go:431 msg="starting runner" cmd="/var/opt/ollama-0.15.6/bin/ollama runner --ollama-engine --port 39917"
time=2026-02-19T19:40:14.522+01:00 level=INFO source=types.go:42 msg="inference compute" id=7201de10-0422-0000-0300-000100000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="NVIDIA GeForce RTX 3090 (NVK GA102)" libdirs=ollama,vulkan driver=0.0 pci_id=0000:03:00.0 type=discrete total="24.2 GiB" available="21.8 GiB"

(...)

time=2026-02-19T19:54:03.049+01:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:7201de10-0422-0000-0300-000100000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-19T19:54:03.049+01:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="11.8 GiB"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="876.0 MiB"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="157.3 MiB"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:272 msg="total memory" size="13.8 GiB"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=sched.go:537 msg="loaded runners" count=1
time=2026-02-19T19:54:03.049+01:00 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-02-19T19:54:03.050+01:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
time=2026-02-19T19:54:11.581+01:00 level=INFO source=server.go:1388 msg="llama runner started in 9.97 seconds"
SIGBUS: bus error
PC=0x7f6d7755a692 m=16 sigcode=2 addr=0x7f6c323af040
signal arrived during cgo execution

goroutine 383 gp=0xc0020a2e00 m=16 mp=0xc000101008 [syscall]:
runtime.cgocall(0x5623aa381c80, 0xc0000a5aa0)
	runtime/cgocall.go:167 +0x4b fp=0xc0000a5a78 sp=0xc0000a5a40 pc=0x5623a953894b
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x7f6cfc00f190, 0x7f6c706929b0)
	_cgo_gotypes.go:979 +0x4a fp=0xc0000a5aa0 sp=0xc0000a5a78 pc=0x5623a99a8cca
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...)
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc0025c2080, 0xc0000ecb00?, {0xc0015b2580, 0x1, 0x2?})
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b2 fp=0xc0000a5b78 sp=0xc0000a5aa0 pc=0x5623a99b7312
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0002550e0, {0x0, {0x5623aac6d8b0, 0xc0025c2080}, {0x5623aac7a340, 0xc001f40648}, {0xc000197208, 0x52, 0x8f}, {{0x5623aac7a340, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc0000a5ef0 sp=0xc0000a5b78 pc=0x5623a9ad5ea2
github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc0000a5fe0 sp=0xc0000a5ef0 pc=0x5623a9ad3b98
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a5fe8 sp=0xc0000a5fe0 pc=0x5623a9543c61
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 14
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd

(...)

rax    0x7f6c323af000
rbx    0x1000
rcx    0x7f6c323af000
rdx    0x7f6c32495900
rdi    0x7f6c323af040
rsi    0x7f6c700f0980
rbp    0x7f6c70691420
rsp    0x7f6cf1afdc48
r8     0x0
r9     0x7f6cfc01e670
r10    0x7f6cfc0aeaf0
r11    0x7f6cfc08d598
r12    0x7f6cec07f9e0
r13    0x7f6cc2501030
r14    0x7f6cfc01efe0
r15    0x7f6cfc00f190
rip    0x7f6d7755a692
rflags 0x10203
cs     0x33
fs     0x0
gs     0x0
time=2026-02-19T19:54:11.958+01:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:34809/completion\": EOF"
[GIN] 2026/02/19 - 19:54:11 | 500 | 10.837667796s |       127.0.0.1 | POST     "/api/generate"

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.15.6

Originally created by @morgwai on GitHub (Feb 19, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14325 ### What is the issue? I wanted to test the perf when using Vulkan+Nouveau comparing to CUDA, so I ran [llm_benchmark](https://github.com/aidatatools/ollama-benchmark), which loads and prompts various models and measures the output. When `gpt-oss:20b` was loaded and prompt `Summarize the key differences between classical and operant conditioning in psychology` issued, the runner crashed due to SIGBUS. I retried 2 times and it happens consistently. It works ok via CUDA. Also when using Vulkan + Nouveau + gpt-oss:20b and issuing the same prompt manually, it works fine, so it must be a very specific chain of events that triggers the bug. OS: Debian-13 kernel: `6.18.5+deb13-amd64` firmware-nvidia-graphics: `20251021-1~bpo13+1` (contains GSP 570.144) Host: TUXEDO InfinityBook Pro 14 - Gen10 - AMD (HX370 APU), 128GB RAM GPU: RTX 3090 server cmd: `OLLAMA_VULKAN=1 GGML_VK_VISIBLE_DEVICES=0 ollama serve` (full log: [ollama-sigbus.log](https://github.com/user-attachments/files/25425115/ollama-sigbus.log)) llm_benchmark version: 0.5.1 llm_benchmark cmd: `llm_benchmark run` (output: [llm-benchmark.log](https://github.com/user-attachments/files/25425083/llm-benchmark.log)) ### Relevant log output ```shell time=2026-02-19T19:40:14.235+01:00 level=INFO source=routes.go:1636 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/home/morgwai/.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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2026-02-19T19:40:14.238+01:00 level=INFO source=images.go:473 msg="total blobs: 67" time=2026-02-19T19:40:14.238+01:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0" time=2026-02-19T19:40:14.239+01:00 level=INFO source=routes.go:1689 msg="Listening on 127.0.0.1:11434 (version 0.15.6)" time=2026-02-19T19:40:14.239+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-02-19T19:40:14.239+01:00 level=WARN source=runner.go:485 msg="user overrode visible devices" GGML_VK_VISIBLE_DEVICES=0 time=2026-02-19T19:40:14.239+01:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again" time=2026-02-19T19:40:14.240+01:00 level=INFO source=server.go:431 msg="starting runner" cmd="/var/opt/ollama-0.15.6/bin/ollama runner --ollama-engine --port 37889" time=2026-02-19T19:40:14.266+01:00 level=INFO source=server.go:431 msg="starting runner" cmd="/var/opt/ollama-0.15.6/bin/ollama runner --ollama-engine --port 34073" time=2026-02-19T19:40:14.283+01:00 level=INFO source=server.go:431 msg="starting runner" cmd="/var/opt/ollama-0.15.6/bin/ollama runner --ollama-engine --port 39917" time=2026-02-19T19:40:14.522+01:00 level=INFO source=types.go:42 msg="inference compute" id=7201de10-0422-0000-0300-000100000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="NVIDIA GeForce RTX 3090 (NVK GA102)" libdirs=ollama,vulkan driver=0.0 pci_id=0000:03:00.0 type=discrete total="24.2 GiB" available="21.8 GiB" (...) time=2026-02-19T19:54:03.049+01:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:7201de10-0422-0000-0300-000100000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-19T19:54:03.049+01:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="11.8 GiB" time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="876.0 MiB" time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="157.3 MiB" time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-02-19T19:54:03.050+01:00 level=INFO source=device.go:272 msg="total memory" size="13.8 GiB" time=2026-02-19T19:54:03.050+01:00 level=INFO source=sched.go:537 msg="loaded runners" count=1 time=2026-02-19T19:54:03.049+01:00 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU" time=2026-02-19T19:54:03.050+01:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-02-19T19:54:03.050+01:00 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU" time=2026-02-19T19:54:03.050+01:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-02-19T19:54:03.050+01:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" time=2026-02-19T19:54:11.581+01:00 level=INFO source=server.go:1388 msg="llama runner started in 9.97 seconds" SIGBUS: bus error PC=0x7f6d7755a692 m=16 sigcode=2 addr=0x7f6c323af040 signal arrived during cgo execution goroutine 383 gp=0xc0020a2e00 m=16 mp=0xc000101008 [syscall]: runtime.cgocall(0x5623aa381c80, 0xc0000a5aa0) runtime/cgocall.go:167 +0x4b fp=0xc0000a5a78 sp=0xc0000a5a40 pc=0x5623a953894b github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x7f6cfc00f190, 0x7f6c706929b0) _cgo_gotypes.go:979 +0x4a fp=0xc0000a5aa0 sp=0xc0000a5a78 pc=0x5623a99a8cca github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc0025c2080, 0xc0000ecb00?, {0xc0015b2580, 0x1, 0x2?}) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b2 fp=0xc0000a5b78 sp=0xc0000a5aa0 pc=0x5623a99b7312 github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0002550e0, {0x0, {0x5623aac6d8b0, 0xc0025c2080}, {0x5623aac7a340, 0xc001f40648}, {0xc000197208, 0x52, 0x8f}, {{0x5623aac7a340, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc0000a5ef0 sp=0xc0000a5b78 pc=0x5623a9ad5ea2 github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc0000a5fe0 sp=0xc0000a5ef0 pc=0x5623a9ad3b98 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a5fe8 sp=0xc0000a5fe0 pc=0x5623a9543c61 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 14 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd (...) rax 0x7f6c323af000 rbx 0x1000 rcx 0x7f6c323af000 rdx 0x7f6c32495900 rdi 0x7f6c323af040 rsi 0x7f6c700f0980 rbp 0x7f6c70691420 rsp 0x7f6cf1afdc48 r8 0x0 r9 0x7f6cfc01e670 r10 0x7f6cfc0aeaf0 r11 0x7f6cfc08d598 r12 0x7f6cec07f9e0 r13 0x7f6cc2501030 r14 0x7f6cfc01efe0 r15 0x7f6cfc00f190 rip 0x7f6d7755a692 rflags 0x10203 cs 0x33 fs 0x0 gs 0x0 time=2026-02-19T19:54:11.958+01:00 level=ERROR source=server.go:1610 msg="post predict" error="Post \"http://127.0.0.1:34809/completion\": EOF" [GIN] 2026/02/19 - 19:54:11 | 500 | 10.837667796s | 127.0.0.1 | POST "/api/generate" ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.15.6
GiteaMirror added the bug label 2026-04-29 09:47:20 -05:00
GiteaMirror commented 2026-04-29 09:47:21 -05:00
Author
Owner
Copy Link

@morgwai commented on GitHub (Feb 19, 2026):

Also happens on ollama-0.16.2 + llm_benchmark-0.5.2.

time=2026-02-19T20:40:48.298+01:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:7201de10-0422-0000-0300-000100000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="11.8 GiB"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="876.0 MiB"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="157.3 MiB"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:272 msg="total memory" size="13.8 GiB"
time=2026-02-19T20:40:48.298+01:00 level=INFO source=sched.go:540 msg="loaded runners" count=1
time=2026-02-19T20:40:48.298+01:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-02-19T20:40:48.299+01:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
time=2026-02-19T20:40:57.077+01:00 level=INFO source=server.go:1388 msg="llama runner started in 10.23 seconds"
SIGBUS: bus error
PC=0x7fb997e97692 m=30 sigcode=2 addr=0x7fb84ea12040
signal arrived during cgo execution

goroutine 621 gp=0xc002042380 m=30 mp=0xc002152808 [syscall]:
runtime.cgocall(0x5562b2d22680, 0xc0000a5aa0)
	runtime/cgocall.go:167 +0x4b fp=0xc0000a5a78 sp=0xc0000a5a40 pc=0x5562b1e32acb
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x7fb9300012a0, 0x7fb81c002ff0)
	_cgo_gotypes.go:979 +0x4a fp=0xc0000a5aa0 sp=0xc0000a5a78 pc=0x5562b230c42a
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...)
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825
github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc000524080, 0xc0000ecb00?, {0xc0006825f0, 0x1, 0x2?})
	github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b2 fp=0xc0000a5b78 sp=0xc0000a5aa0 pc=0x5562b231aa72
github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0002550e0, {0x0, {0x5562b365fbf0, 0xc000524080}, {0x5562b366cc40, 0xc002508120}, {0xc00027d688, 0x52, 0x8f}, {{0x5562b366cc40, ...}, ...}, ...})
	github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc0000a5ef0 sp=0xc0000a5b78 pc=0x5562b2439602
github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1()
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc0000a5fe0 sp=0xc0000a5ef0 pc=0x5562b24372f8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a5fe8 sp=0xc0000a5fe0 pc=0x5562b1e3dec1
created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 57
	github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd
<!-- gh-comment-id:3929514969 --> @morgwai commented on GitHub (Feb 19, 2026): Also happens on ollama-0.16.2 + llm_benchmark-0.5.2. ``` time=2026-02-19T20:40:48.298+01:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:7201de10-0422-0000-0300-000100000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-19T20:40:48.298+01:00 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU" time=2026-02-19T20:40:48.298+01:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-02-19T20:40:48.298+01:00 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU" time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="11.8 GiB" time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="876.0 MiB" time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="157.3 MiB" time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-02-19T20:40:48.298+01:00 level=INFO source=device.go:272 msg="total memory" size="13.8 GiB" time=2026-02-19T20:40:48.298+01:00 level=INFO source=sched.go:540 msg="loaded runners" count=1 time=2026-02-19T20:40:48.298+01:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding" time=2026-02-19T20:40:48.299+01:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model" time=2026-02-19T20:40:57.077+01:00 level=INFO source=server.go:1388 msg="llama runner started in 10.23 seconds" SIGBUS: bus error PC=0x7fb997e97692 m=30 sigcode=2 addr=0x7fb84ea12040 signal arrived during cgo execution goroutine 621 gp=0xc002042380 m=30 mp=0xc002152808 [syscall]: runtime.cgocall(0x5562b2d22680, 0xc0000a5aa0) runtime/cgocall.go:167 +0x4b fp=0xc0000a5a78 sp=0xc0000a5a40 pc=0x5562b1e32acb github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x7fb9300012a0, 0x7fb81c002ff0) _cgo_gotypes.go:979 +0x4a fp=0xc0000a5aa0 sp=0xc0000a5a78 pc=0x5562b230c42a github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify.func2(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 github.com/ollama/ollama/ml/backend/ggml.(*Context).ComputeWithNotify(0xc000524080, 0xc0000ecb00?, {0xc0006825f0, 0x1, 0x2?}) github.com/ollama/ollama/ml/backend/ggml/ggml.go:825 +0x1b2 fp=0xc0000a5b78 sp=0xc0000a5aa0 pc=0x5562b231aa72 github.com/ollama/ollama/runner/ollamarunner.(*Server).computeBatch(0xc0002550e0, {0x0, {0x5562b365fbf0, 0xc000524080}, {0x5562b366cc40, 0xc002508120}, {0xc00027d688, 0x52, 0x8f}, {{0x5562b366cc40, ...}, ...}, ...}) github.com/ollama/ollama/runner/ollamarunner/runner.go:716 +0x862 fp=0xc0000a5ef0 sp=0xc0000a5b78 pc=0x5562b2439602 github.com/ollama/ollama/runner/ollamarunner.(*Server).run.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x58 fp=0xc0000a5fe0 sp=0xc0000a5ef0 pc=0x5562b24372f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a5fe8 sp=0xc0000a5fe0 pc=0x5562b1e3dec1 created by github.com/ollama/ollama/runner/ollamarunner.(*Server).run in goroutine 57 github.com/ollama/ollama/runner/ollamarunner/runner.go:459 +0x2cd ```
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#55833
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?