github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12314] Debian 13, rocm 7.0 --> [signal SIGSEGV: segmentation violation #70240

New Issue
Open
opened 2026-05-04 20:45:32 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 20:45:32 -05:00
Owner
Copy Link

Originally created by @mistersixt on GitHub (Sep 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12314

What is the issue?

Hi there,

I upgraded by workstation from Debian 12 to 13 + from rocm 6.4.1 to rocm 7.0. With every "run" of a model ollama server crashes with SIGSEGV, please find all details below.

Kind regards, mistersixt.

Relevant log output

jomo@lammbock:~$ ollama run devstral:latest
Error: 500 Internal Server Error: do load request: Post "http://127.0.0.1:42089/load": EOF
jomo@lammbock:~$ lsb_release -a
No LSB modules are available.
Distributor ID:	Debian
Description:	Debian GNU/Linux 13 (trixie)
Release:	13
Codename:	trixie
jomo@lammbock:~$ uname -r
6.12.43+deb13-amd64
jomo@lammbock:~$ lspci -v | grep -A1 VGA
0a:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Navi 32 [Radeon RX 7700 XT / 7800 XT] (rev ff) (prog-if 00 [VGA controller])
	Subsystem: ASUSTeK Computer Inc. Device 0516
jomo@lammbock:~$ dpkg -l | grep rocm
ii  rocm-core                                           7.0.0.70000-38~24.04                    amd64        ROCm Runtime software stack
ii  rocminfo                                            1.0.0.70000-38~24.04                    amd64        Radeon Open Compute (ROCm) Runtime rocminfo tool
jomo@lammbock:~$ /opt/rocm/bin/rocminfo | grep -A2 Agent
HSA Agents               
==========               
*******                  
Agent 1                  
*******                  
  Name:                    AMD Ryzen 7 3700X 8-Core Processor 
--
Agent 2                  
*******                  
  Name:                    gfx1101                            
jomo@lammbock:~$

(...from journalctrl...)
...
Sep 17 08:56:36 lammbock ollama[2768272]: time=2025-09-17T08:56:36.484+02:00 level=INFO source=runner.go:864 msg="starting go runner"
Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: found 1 ROCm devices:
Sep 17 08:56:37 lammbock ollama[2768272]:   Device 0: AMD Radeon RX 7700 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32, ID: GPU-3065d3ad3268ec08
Sep 17 08:56:37 lammbock ollama[2768272]: load_backend: loaded ROCm backend from /usr/lib/ollama/libggml-hip.so
Sep 17 08:56:37 lammbock ollama[2768272]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: found 1 ROCm devices:
Sep 17 08:56:37 lammbock ollama[2768272]:   Device 0: AMD Radeon RX 7700 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32
Sep 17 08:56:37 lammbock ollama[2768272]: load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so
Sep 17 08:56:37 lammbock ollama[2768272]: time=2025-09-17T08:56:37.326+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 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
Sep 17 08:56:37 lammbock ollama[2768272]: time=2025-09-17T08:56:37.326+02:00 level=INFO source=runner.go:900 msg="Server listening on 127.0.0.1:42089"
Sep 17 08:56:37 lammbock ollama[2768272]: time=2025-09-17T08:56:37.329+02:00 level=INFO source=runner.go:799 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:28[ID:GPU-3065d3ad3268ec08 Layers:28(12..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:true}"
Sep 17 08:56:37 lammbock ollama[2768272]: unexpected fault address 0x2f2a00000
Sep 17 08:56:37 lammbock ollama[2768272]: fatal error: fault
Sep 17 08:56:37 lammbock ollama[2768272]: [signal SIGSEGV: segmentation violation code=0x1 addr=0x2f2a00000 pc=0x55f5410632a0]
Sep 17 08:56:37 lammbock ollama[2768272]: goroutine 33 gp=0xc0005828c0 m=7 mp=0xc000580008 [running]:
Sep 17 08:56:37 lammbock ollama[2768272]: runtime.throw({0x55f542098499?, 0xc0005828c0?})
Sep 17 08:56:37 lammbock ollama[2768272]:         runtime/panic.go:1096 +0x4a fp=0xc000049678 sp=0xc000049648 pc=0x55f5410d374a
Sep 17 08:56:37 lammbock ollama[2768272]: runtime.sigpanic()
Sep 17 08:56:37 lammbock ollama[2768272]:         runtime/signal_unix.go:939 +0x26c fp=0xc0000496d8 sp=0xc000049678 pc=0x55f5410d5bcc
Sep 17 08:56:37 lammbock ollama[2768272]: indexbytebody()
Sep 17 08:56:37 lammbock ollama[2768272]:         internal/bytealg/indexbyte_amd64.s:131 +0xe0 fp=0xc0000496e0 sp=0xc0000496d8 pc=0x55f5410632a0
Sep 17 08:56:37 lammbock ollama[2768272]: runtime.findnull(0xc000049760?)
Sep 17 08:56:37 lammbock ollama[2768272]:         runtime/string.go:577 +0x79 fp=0xc000049738 sp=0xc0000496e0 pc=0x55f5410bb3d9
Sep 17 08:56:37 lammbock ollama[2768272]: runtime.gostring(0x2f2a00000)
Sep 17 08:56:37 lammbock ollama[2768272]:         runtime/string.go:363 +0x1c fp=0xc000049770 sp=0xc000049738 pc=0x55f5410d6a3c
Sep 17 08:56:37 lammbock ollama[2768272]: github.com/ollama/ollama/llama._Cfunc_GoString(...)
Sep 17 08:56:37 lammbock ollama[2768272]:         _cgo_gotypes.go:332
...

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.11.11

Originally created by @mistersixt on GitHub (Sep 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12314 ### What is the issue? Hi there, I upgraded by workstation from Debian 12 to 13 + from rocm 6.4.1 to rocm 7.0. With every "run" of a model ollama server crashes with SIGSEGV, please find all details below. Kind regards, mistersixt. ### Relevant log output ```shell jomo@lammbock:~$ ollama run devstral:latest Error: 500 Internal Server Error: do load request: Post "http://127.0.0.1:42089/load": EOF jomo@lammbock:~$ lsb_release -a No LSB modules are available. Distributor ID: Debian Description: Debian GNU/Linux 13 (trixie) Release: 13 Codename: trixie jomo@lammbock:~$ uname -r 6.12.43+deb13-amd64 jomo@lammbock:~$ lspci -v | grep -A1 VGA 0a:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Navi 32 [Radeon RX 7700 XT / 7800 XT] (rev ff) (prog-if 00 [VGA controller]) Subsystem: ASUSTeK Computer Inc. Device 0516 jomo@lammbock:~$ dpkg -l | grep rocm ii rocm-core 7.0.0.70000-38~24.04 amd64 ROCm Runtime software stack ii rocminfo 1.0.0.70000-38~24.04 amd64 Radeon Open Compute (ROCm) Runtime rocminfo tool jomo@lammbock:~$ /opt/rocm/bin/rocminfo | grep -A2 Agent HSA Agents ========== ******* Agent 1 ******* Name: AMD Ryzen 7 3700X 8-Core Processor -- Agent 2 ******* Name: gfx1101 jomo@lammbock:~$ (...from journalctrl...) ... Sep 17 08:56:36 lammbock ollama[2768272]: time=2025-09-17T08:56:36.484+02:00 level=INFO source=runner.go:864 msg="starting go runner" Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: found 1 ROCm devices: Sep 17 08:56:37 lammbock ollama[2768272]: Device 0: AMD Radeon RX 7700 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32, ID: GPU-3065d3ad3268ec08 Sep 17 08:56:37 lammbock ollama[2768272]: load_backend: loaded ROCm backend from /usr/lib/ollama/libggml-hip.so Sep 17 08:56:37 lammbock ollama[2768272]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Sep 17 08:56:37 lammbock ollama[2768272]: ggml_cuda_init: found 1 ROCm devices: Sep 17 08:56:37 lammbock ollama[2768272]: Device 0: AMD Radeon RX 7700 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32 Sep 17 08:56:37 lammbock ollama[2768272]: load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so Sep 17 08:56:37 lammbock ollama[2768272]: time=2025-09-17T08:56:37.326+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 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) Sep 17 08:56:37 lammbock ollama[2768272]: time=2025-09-17T08:56:37.326+02:00 level=INFO source=runner.go:900 msg="Server listening on 127.0.0.1:42089" Sep 17 08:56:37 lammbock ollama[2768272]: time=2025-09-17T08:56:37.329+02:00 level=INFO source=runner.go:799 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:28[ID:GPU-3065d3ad3268ec08 Layers:28(12..39)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:true}" Sep 17 08:56:37 lammbock ollama[2768272]: unexpected fault address 0x2f2a00000 Sep 17 08:56:37 lammbock ollama[2768272]: fatal error: fault Sep 17 08:56:37 lammbock ollama[2768272]: [signal SIGSEGV: segmentation violation code=0x1 addr=0x2f2a00000 pc=0x55f5410632a0] Sep 17 08:56:37 lammbock ollama[2768272]: goroutine 33 gp=0xc0005828c0 m=7 mp=0xc000580008 [running]: Sep 17 08:56:37 lammbock ollama[2768272]: runtime.throw({0x55f542098499?, 0xc0005828c0?}) Sep 17 08:56:37 lammbock ollama[2768272]: runtime/panic.go:1096 +0x4a fp=0xc000049678 sp=0xc000049648 pc=0x55f5410d374a Sep 17 08:56:37 lammbock ollama[2768272]: runtime.sigpanic() Sep 17 08:56:37 lammbock ollama[2768272]: runtime/signal_unix.go:939 +0x26c fp=0xc0000496d8 sp=0xc000049678 pc=0x55f5410d5bcc Sep 17 08:56:37 lammbock ollama[2768272]: indexbytebody() Sep 17 08:56:37 lammbock ollama[2768272]: internal/bytealg/indexbyte_amd64.s:131 +0xe0 fp=0xc0000496e0 sp=0xc0000496d8 pc=0x55f5410632a0 Sep 17 08:56:37 lammbock ollama[2768272]: runtime.findnull(0xc000049760?) Sep 17 08:56:37 lammbock ollama[2768272]: runtime/string.go:577 +0x79 fp=0xc000049738 sp=0xc0000496e0 pc=0x55f5410bb3d9 Sep 17 08:56:37 lammbock ollama[2768272]: runtime.gostring(0x2f2a00000) Sep 17 08:56:37 lammbock ollama[2768272]: runtime/string.go:363 +0x1c fp=0xc000049770 sp=0xc000049738 pc=0x55f5410d6a3c Sep 17 08:56:37 lammbock ollama[2768272]: github.com/ollama/ollama/llama._Cfunc_GoString(...) Sep 17 08:56:37 lammbock ollama[2768272]: _cgo_gotypes.go:332 ... ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.11.11
GiteaMirror added the bug label 2026-05-04 20:45:32 -05:00
GiteaMirror commented 2026-05-04 20:45:35 -05:00
Author
Owner
Copy Link

@Mubelotix commented on GitHub (Nov 13, 2025):

I can confirm

Logs 
ansible@server:~$ sudo dmesg | grep amdgpu
[    0.000000] Command line: BOOT_IMAGE=/boot/vmlinuz-6.16.3+deb13-amd64 root=UUID=056a13c4-d1c6-4879-8008-b0bb5544c1b7 ro quiet amdgpu.virtual_display=0000:c6:00.0,1 amdgpu.gpu_recovery=1
[    0.009612] Kernel command line: BOOT_IMAGE=/boot/vmlinuz-6.16.3+deb13-amd64 root=UUID=056a13c4-d1c6-4879-8008-b0bb5544c1b7 ro quiet amdgpu.virtual_display=0000:c6:00.0,1 amdgpu.gpu_recovery=1
[    3.269250] [drm] amdgpu kernel modesetting enabled.
[    3.274888] amdgpu: Virtual CRAT table created for CPU
[    3.274905] amdgpu: Topology: Add CPU node
[    3.275000] amdgpu 0000:c6:00.0: enabling device (0006 -> 0007)
[    3.278571] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 0 <soc21_common>
[    3.278575] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 1 <gmc_v11_0>
[    3.278577] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 2 <ih_v6_0>
[    3.278579] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 3 <psp>
[    3.278581] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 4 <smu>
[    3.278583] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 5 <amdgpu_vkms>
[    3.278585] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 6 <gfx_v11_0>
[    3.278587] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 7 <sdma_v6_0>
[    3.278589] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 8 <vcn_v4_0>
[    3.278591] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 9 <jpeg_v4_0>
[    3.278592] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 10 <mes_v11_0>
[    3.278607] amdgpu 0000:c6:00.0: amdgpu: Fetched VBIOS from VFCT
[    3.278609] amdgpu: ATOM BIOS: 113-PHXGENERIC-001
[    3.287740] amdgpu 0000:c6:00.0: vgaarb: deactivate vga console
[    3.287745] amdgpu 0000:c6:00.0: amdgpu: Trusted Memory Zone (TMZ) feature enabled
[    3.287825] amdgpu 0000:c6:00.0: amdgpu: VRAM: 4096M 0x0000008000000000 - 0x00000080FFFFFFFF (4096M used)
[    3.287827] amdgpu 0000:c6:00.0: amdgpu: GART: 512M 0x00007FFF00000000 - 0x00007FFF1FFFFFFF
[    3.288037] [drm] amdgpu: 4096M of VRAM memory ready
[    3.288039] [drm] amdgpu: 5895M of GTT memory ready.
[    3.289553] amdgpu 0000:c6:00.0: amdgpu: Found VCN firmware Version ENC: 1.23 DEC: 9 VEP: 0 Revision: 15
[    3.315004] amdgpu 0000:c6:00.0: amdgpu: reserve 0x4000000 from 0x80f8000000 for PSP TMR
[    3.786275] amdgpu 0000:c6:00.0: amdgpu: RAS: optional ras ta ucode is not available
[    3.794536] amdgpu 0000:c6:00.0: amdgpu: RAP: optional rap ta ucode is not available
[    3.794544] amdgpu 0000:c6:00.0: amdgpu: SECUREDISPLAY: optional securedisplay ta ucode is not available
[    3.826991] amdgpu 0000:c6:00.0: amdgpu: SMU is initialized successfully!
[    3.835317] kfd kfd: amdgpu: Allocated 3969056 bytes on gart
[    3.835334] kfd kfd: amdgpu: Total number of KFD nodes to be created: 1
[    3.835989] amdgpu: Virtual CRAT table created for GPU
[    3.836143] amdgpu: Topology: Add dGPU node [0x1900:0x1002]
[    3.836145] kfd kfd: amdgpu: added device 1002:1900
[    3.836157] amdgpu 0000:c6:00.0: amdgpu: SE 1, SH per SE 2, CU per SH 6, active_cu_number 12
[    3.836163] amdgpu 0000:c6:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[    3.836166] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[    3.836167] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[    3.836168] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
[    3.836170] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
[    3.836171] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
[    3.836172] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
[    3.836173] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
[    3.836175] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
[    3.836176] amdgpu 0000:c6:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[    3.836177] amdgpu 0000:c6:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[    3.836178] amdgpu 0000:c6:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
[    3.836180] amdgpu 0000:c6:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
[    3.837387] amdgpu 0000:c6:00.0: amdgpu: Runtime PM not available
[    3.837556] [drm] Initialized amdgpu 3.64.0 for 0000:c6:00.0 on minor 0
[    3.840048] fbcon: amdgpudrmfb (fb0) is primary device
[    3.873996] amdgpu 0000:c6:00.0: [drm] fb0: amdgpudrmfb frame buffer device
ansible@server:~$ sudo docker stop ollama
ollama
ansible@server:~$ sudo docker rm ollama
ollama
ansible@server:~$ sudo docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 11434:11434 --name ollama -e HSA_OVERRIDE_GFX_VERSION=11.0.0 -e HSA_ENABLE_SDMA=0 -e HCC_AMDGPU_TARGET=gfx1103_r1 ollama/ollama:rocm
7fac4a565313628f9c42e6db4ffbf625deeac3fc6a1a4f7fb725924182306dd8
ansible@server:~$ sudo docker logs ollama
2025/11/13 18:37:07 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:11.0.0 HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-11-13T18:37:07.937Z level=INFO source=images.go:432 msg="total blobs: 12"
time=2025-11-13T18:37:07.937Z level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-11-13T18:37:07.938Z level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)"
time=2025-11-13T18:37:07.938Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-11-13T18:37:07.939Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2025-11-13T18:37:07.939Z level=INFO source=amd_linux.go:389 msg="skipping rocm gfx compatibility check" HSA_OVERRIDE_GFX_VERSION=11.0.0
time=2025-11-13T18:37:07.939Z level=INFO source=types.go:130 msg="inference compute" id=0 library=rocm variant="" compute=gfx1103 driver=0.0 name=1002:1900 total="4.0 GiB" available="3.9 GiB"
ansible@server:~$ sudo docker exec -it ollama ollama run qwen:0.5b
Error: llama runner process has terminated: exit status 2
ansible@server:~$ sudo docker logs ollama
2025/11/13 18:37:07 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:11.0.0 HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-11-13T18:37:07.937Z level=INFO source=images.go:432 msg="total blobs: 12"
time=2025-11-13T18:37:07.937Z level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-11-13T18:37:07.938Z level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)"
time=2025-11-13T18:37:07.938Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-11-13T18:37:07.939Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2025-11-13T18:37:07.939Z level=INFO source=amd_linux.go:389 msg="skipping rocm gfx compatibility check" HSA_OVERRIDE_GFX_VERSION=11.0.0
time=2025-11-13T18:37:07.939Z level=INFO source=types.go:130 msg="inference compute" id=0 library=rocm variant="" compute=gfx1103 driver=0.0 name=1002:1900 total="4.0 GiB" available="3.9 GiB"
[GIN] 2025/11/13 - 18:37:27 | 200 |      33.012µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/11/13 - 18:37:27 | 200 |   10.801318ms |       127.0.0.1 | POST     "/api/show"
time=2025-11-13T18:37:27.857Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-fad2a06e4cc705c2fa8bec5477ddb00dc0c859ac184c34dcc5586663774161ca gpu=0 parallel=4 available=4220772352 required="1.8 GiB"
time=2025-11-13T18:37:27.857Z level=INFO source=server.go:100 msg="system memory" total="11.5 GiB" free="9.5 GiB" free_swap="976.0 MiB"
time=2025-11-13T18:37:27.858Z level=INFO source=memory.go:356 msg="offload to rocm" layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[3.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.8 GiB" memory.required.partial="1.8 GiB" memory.required.kv="768.0 MiB" memory.required.allocations="[1.8 GiB]" memory.weights.total="933.8 MiB" memory.weights.repeating="812.1 MiB" memory.weights.nonrepeating="121.7 MiB" memory.graph.full="298.8 MiB" memory.graph.partial="420.5 MiB"
time=2025-11-13T18:37:27.858Z level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-fad2a06e4cc705c2fa8bec5477ddb00dc0c859ac184c34dcc5586663774161ca --ctx-size 8192 --batch-size 512 --n-gpu-layers 25 --threads 8 --parallel 4 --port 37589"
time=2025-11-13T18:37:27.859Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-11-13T18:37:27.859Z level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-11-13T18:37:27.859Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-11-13T18:37:27.867Z level=INFO source=runner.go:936 msg="starting go runner"
time=2025-11-13T18:37:27.867Z level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=8
time=2025-11-13T18:37:27.867Z level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:37589"
/opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory
time=2025-11-13T18:37:28.111Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon Graphics, compute capability 11.0, VMM: no
load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so
llama_load_model_from_file: using device ROCm0 (AMD Radeon Graphics) - 5816 MiB free
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-fad2a06e4cc705c2fa8bec5477ddb00dc0c859ac184c34dcc5586663774161ca (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen2
llama_model_loader: - kv   1:                               general.name str              = Qwen2-beta-0_5B-Chat
llama_model_loader: - kv   2:                          qwen2.block_count u32              = 24
llama_model_loader: - kv   3:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv   4:                     qwen2.embedding_length u32              = 1024
llama_model_loader: - kv   5:                  qwen2.feed_forward_length u32              = 2816
llama_model_loader: - kv   6:                 qwen2.attention.head_count u32              = 16
llama_model_loader: - kv   7:              qwen2.attention.head_count_kv u32              = 16
llama_model_loader: - kv   8:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv   9:                qwen2.use_parallel_residual bool             = true
llama_model_loader: - kv  10:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  11:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  12:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  13:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  14:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  15:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  17:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
llama_model_loader: - kv  18:               general.quantization_version u32              = 2
llama_model_loader: - kv  19:                          general.file_type u32              = 2
llama_model_loader: - type  f32:  121 tensors
llama_model_loader: - type q4_0:  169 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default'
llm_load_vocab: special tokens cache size = 293
llm_load_vocab: token to piece cache size = 0.9338 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 151936
llm_load_print_meta: n_merges         = 151387
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 1024
llm_load_print_meta: n_layer          = 24
llm_load_print_meta: n_head           = 16
llm_load_print_meta: n_head_kv        = 16
llm_load_print_meta: n_rot            = 64
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 64
llm_load_print_meta: n_embd_head_v    = 64
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-06
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 2816
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 2
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 32768
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 0.5B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 619.57 M
llm_load_print_meta: model size       = 371.02 MiB (5.02 BPW) 
llm_load_print_meta: general.name     = Qwen2-beta-0_5B-Chat
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 148848 'ÄĬ'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: max token length = 256
SIGSEGV: segmentation violation
PC=0x7f7135082c2d m=3 sigcode=1 addr=0x18
signal arrived during cgo execution

goroutine 51 gp=0xc0005048c0 m=3 mp=0xc00007ce08 [syscall]:
runtime.cgocall(0x55eba088f540, 0xc000093b78)
	runtime/cgocall.go:167 +0x4b fp=0xc000093b50 sp=0xc000093b18 pc=0x55eb9fce7c2b
github.com/ollama/ollama/llama._Cfunc_llama_load_model_from_file(0x7f7140c6ade0, {0x0, 0x19, 0x1, 0x0, 0x0, 0x0, 0x55eba088ef50, 0xc000014088, 0x0, ...})
	_cgo_gotypes.go:689 +0x50 fp=0xc000093b78 sp=0xc000093b50 pc=0x55eba009d590
github.com/ollama/ollama/llama.LoadModelFromFile.func1({0x7ffe84b23d70?, 0xc0005048c0?}, {0x0, 0x19, 0x1, 0x0, 0x0, 0x0, 0x55eba088ef50, 0xc000014088, ...})
	github.com/ollama/ollama/llama/llama.go:271 +0x127 fp=0xc000093c78 sp=0xc000093b78 pc=0x55eba00a0d87
github.com/ollama/ollama/llama.LoadModelFromFile({0x7ffe84b23d70, 0x62}, {0x19, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc000117f70, ...})
	github.com/ollama/ollama/llama/llama.go:271 +0x2d6 fp=0xc000093dc8 sp=0xc000093c78 pc=0x55eba00a0a76
github.com/ollama/ollama/llama/runner.(*Server).loadModel(0xc0001a9560, {0x19, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc000117f70, 0x0}, ...)
	github.com/ollama/ollama/llama/runner/runner.go:850 +0xb2 fp=0xc000093f10 sp=0xc000093dc8 pc=0x55eba00adab2
github.com/ollama/ollama/llama/runner.Execute.gowrap1()
	github.com/ollama/ollama/llama/runner/runner.go:970 +0xda fp=0xc000093fe0 sp=0xc000093f10 pc=0x55eba00af41a
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x55eb9fcf6701
created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1
	github.com/ollama/ollama/llama/runner/runner.go:970 +0xd0d

goroutine 1 gp=0xc0000061c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc0005155e8 sp=0xc0005155c8 pc=0x55eb9fcee32e
runtime.netpollblock(0xc000519f80?, 0x9fc85146?, 0xeb?)
	runtime/netpoll.go:575 +0xf7 fp=0xc000515620 sp=0xc0005155e8 pc=0x55eb9fcb1f97
internal/poll.runtime_pollWait(0x7f7195653680, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc000515640 sp=0xc000515620 pc=0x55eb9fced625
internal/poll.(*pollDesc).wait(0xc0004c0f80?, 0x2c?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000515668 sp=0xc000515640 pc=0x55eb9fd74de7
internal/poll.(*pollDesc).waitRead(...)
	internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc0004c0f80)
	internal/poll/fd_unix.go:620 +0x295 fp=0xc000515710 sp=0xc000515668 pc=0x55eb9fd7a1b5
net.(*netFD).accept(0xc0004c0f80)
	net/fd_unix.go:172 +0x29 fp=0xc0005157c8 sp=0xc000515710 pc=0x55eb9fde32a9
net.(*TCPListener).accept(0xc000122b40)
	net/tcpsock_posix.go:159 +0x1e fp=0xc000515818 sp=0xc0005157c8 pc=0x55eb9fdf8f1e
net.(*TCPListener).Accept(0xc000122b40)
	net/tcpsock.go:372 +0x30 fp=0xc000515848 sp=0xc000515818 pc=0x55eb9fdf7dd0
net/http.(*onceCloseListener).Accept(0xc000518000?)
	<autogenerated>:1 +0x24 fp=0xc000515860 sp=0xc000515848 pc=0x55eba0042044
net/http.(*Server).Serve(0xc000146a50, {0x55eba0ebabf0, 0xc000122b40})
	net/http/server.go:3330 +0x30c fp=0xc000515990 sp=0xc000515860 pc=0x55eba0019fcc
github.com/ollama/ollama/llama/runner.Execute({0xc000036110?, 0x0?, 0x0?})
	github.com/ollama/ollama/llama/runner/runner.go:996 +0x11a9 fp=0xc000515d30 sp=0xc000515990 pc=0x55eba00aefe9
github.com/ollama/ollama/cmd.NewCLI.func2(0xc000118f00?, {0x55eba0a7d01a?, 0x4?, 0x55eba0a7d01e?})
	github.com/ollama/ollama/cmd/cmd.go:1277 +0x45 fp=0xc000515d58 sp=0xc000515d30 pc=0x55eba088e905
github.com/spf13/cobra.(*Command).execute(0xc0004e7b08, {0xc0001337a0, 0xe, 0xe})
	github.com/spf13/cobra@v1.7.0/command.go:940 +0x862 fp=0xc000515e78 sp=0xc000515d58 pc=0x55eb9fe5bfe2
github.com/spf13/cobra.(*Command).ExecuteC(0xc00046db08)
	github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000515f30 sp=0xc000515e78 pc=0x55eb9fe5c825
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=0xc000515f50 sp=0xc000515f30 pc=0x55eba088ec8d
runtime.main()
	runtime/proc.go:272 +0x29d fp=0xc000515fe0 sp=0xc000515f50 pc=0x55eb9fcb963d
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000515fe8 sp=0xc000515fe0 pc=0x55eb9fcf6701

goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000084fa8 sp=0xc000084f88 pc=0x55eb9fcee32e
runtime.goparkunlock(...)
	runtime/proc.go:430
runtime.forcegchelper()
	runtime/proc.go:337 +0xb8 fp=0xc000084fe0 sp=0xc000084fa8 pc=0x55eb9fcb9978
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000084fe8 sp=0xc000084fe0 pc=0x55eb9fcf6701
created by runtime.init.7 in goroutine 1
	runtime/proc.go:325 +0x1a

goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000085780 sp=0xc000085760 pc=0x55eb9fcee32e
runtime.goparkunlock(...)
	runtime/proc.go:430
runtime.bgsweep(0xc00003e080)
	runtime/mgcsweep.go:317 +0xdf fp=0xc0000857c8 sp=0xc000085780 pc=0x55eb9fca401f
runtime.gcenable.gowrap1()
	runtime/mgc.go:204 +0x25 fp=0xc0000857e0 sp=0xc0000857c8 pc=0x55eb9fc98665
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000857e8 sp=0xc0000857e0 pc=0x55eb9fcf6701
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x55eba0c23c48?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x55eb9fcee32e
runtime.goparkunlock(...)
	runtime/proc.go:430
runtime.(*scavengerState).park(0x55eba1669820)
	runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x55eb9fca19e9
runtime.bgscavenge(0xc00003e080)
	runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x55eb9fca1f79
runtime.gcenable.gowrap2()
	runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x55eb9fc98605
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x55eb9fcf6701
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]:
runtime.gopark(0xc000084648?, 0x55eb9fc8eb65?, 0xb0?, 0x1?, 0xc0000061c0?)
	runtime/proc.go:424 +0xce fp=0xc000084620 sp=0xc000084600 pc=0x55eb9fcee32e
runtime.runfinq()
	runtime/mfinal.go:193 +0x107 fp=0xc0000847e0 sp=0xc000084620 pc=0x55eb9fc976e7
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000847e8 sp=0xc0000847e0 pc=0x55eb9fcf6701
created by runtime.createfing in goroutine 1
	runtime/mfinal.go:163 +0x3d

goroutine 6 gp=0xc0001c7500 m=nil [chan receive]:
runtime.gopark(0xc000086760?, 0x55eb9fdca925?, 0x70?, 0x8?, 0x55eba0ece880?)
	runtime/proc.go:424 +0xce fp=0xc000086718 sp=0xc0000866f8 pc=0x55eb9fcee32e
runtime.chanrecv(0xc0000b8310, 0x0, 0x1)
	runtime/chan.go:639 +0x41c fp=0xc000086790 sp=0xc000086718 pc=0x55eb9fc87d5c
runtime.chanrecv1(0x0?, 0x0?)
	runtime/chan.go:489 +0x12 fp=0xc0000867b8 sp=0xc000086790 pc=0x55eb9fc87912
runtime.unique_runtime_registerUniqueMapCleanup.func1(...)
	runtime/mgc.go:1781
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
	runtime/mgc.go:1784 +0x2f fp=0xc0000867e0 sp=0xc0000867b8 pc=0x55eb9fc9b6cf
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000867e8 sp=0xc0000867e0 pc=0x55eb9fcf6701
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	runtime/mgc.go:1779 +0x96

goroutine 7 gp=0xc0001c7dc0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000086f38 sp=0xc000086f18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc000086fc8 sp=0xc000086f38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc000086fe0 sp=0xc000086fc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000086fe8 sp=0xc000086fe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 8 gp=0xc0004a4000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000087738 sp=0xc000087718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc0000877c8 sp=0xc000087738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc0000877e0 sp=0xc0000877c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000877e8 sp=0xc0000877e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 9 gp=0xc0004a41c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000087f38 sp=0xc000087f18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc000087fc8 sp=0xc000087f38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc000087fe0 sp=0xc000087fc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 10 gp=0xc0004a4380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000080738 sp=0xc000080718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc0000807c8 sp=0xc000080738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc0000807e0 sp=0xc0000807c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000807e8 sp=0xc0000807e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 11 gp=0xc0004a4540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000080f38 sp=0xc000080f18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc000080fc8 sp=0xc000080f38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc000080fe0 sp=0xc000080fc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 12 gp=0xc0004a4700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000081738 sp=0xc000081718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc0000817c8 sp=0xc000081738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc0000817e0 sp=0xc0000817c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000817e8 sp=0xc0000817e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 13 gp=0xc0004a48c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000081f38 sp=0xc000081f18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc000081fc8 sp=0xc000081f38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc000081fe0 sp=0xc000081fc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 14 gp=0xc0004a4a80 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000082738 sp=0xc000082718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc0000827c8 sp=0xc000082738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc0000827e0 sp=0xc0000827c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000827e8 sp=0xc0000827e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 18 gp=0xc000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 34 gp=0xc000104380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 15 gp=0xc0004a4c40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000082f38 sp=0xc000082f18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc000082fc8 sp=0xc000082f38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc000082fe0 sp=0xc000082fc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000082fe8 sp=0xc000082fe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 35 gp=0xc000104540 m=nil [GC worker (idle)]:
runtime.gopark(0x189afdba467?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000506f38 sp=0xc000506f18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc000506fc8 sp=0xc000506f38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc000506fe0 sp=0xc000506fc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000506fe8 sp=0xc000506fe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 16 gp=0xc0004a4e00 m=nil [GC worker (idle)]:
runtime.gopark(0x55eba1717e80?, 0x1?, 0x5d?, 0xba?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000083738 sp=0xc000083718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc0000837c8 sp=0xc000083738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc0000837e0 sp=0xc0000837c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000837e8 sp=0xc0000837e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 19 gp=0xc0005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x55eba1717e80?, 0x1?, 0x84?, 0x5c?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 50 gp=0xc0004a4fc0 m=nil [GC worker (idle)]:
runtime.gopark(0x55eba1717e80?, 0x1?, 0x1?, 0xd?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc000083f38 sp=0xc000083f18 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc000083fc8 sp=0xc000083f38 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 20 gp=0xc000504380 m=nil [GC worker (idle)]:
runtime.gopark(0x55eba1717e80?, 0x1?, 0x77?, 0xbc?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x55eb9fcee32e
runtime.gcBgMarkWorker(0xc0000b98f0)
	runtime/mgc.go:1412 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x55eb9fc9a9c9
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1328 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x55eb9fc9a8a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x55eb9fcf6701
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1328 +0x105

goroutine 52 gp=0xc000504a80 m=nil [semacquire]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:424 +0xce fp=0xc00050de18 sp=0xc00050ddf8 pc=0x55eb9fcee32e
runtime.goparkunlock(...)
	runtime/proc.go:430
runtime.semacquire1(0xc0001a9568, 0x0, 0x1, 0x0, 0x12)
	runtime/sema.go:178 +0x22c fp=0xc00050de80 sp=0xc00050de18 pc=0x55eb9fccc6ec
sync.runtime_Semacquire(0x0?)
	runtime/sema.go:71 +0x25 fp=0xc00050deb8 sp=0xc00050de80 pc=0x55eb9fcefb45
sync.(*WaitGroup).Wait(0x0?)
	sync/waitgroup.go:118 +0x48 fp=0xc00050dee0 sp=0xc00050deb8 pc=0x55eb9fd04f28
github.com/ollama/ollama/llama/runner.(*Server).run(0xc0001a9560, {0x55eba0ebcf40, 0xc000127540})
	github.com/ollama/ollama/llama/runner/runner.go:315 +0x47 fp=0xc00050dfb8 sp=0xc00050dee0 pc=0x55eba00aa287
github.com/ollama/ollama/llama/runner.Execute.gowrap2()
	github.com/ollama/ollama/llama/runner/runner.go:975 +0x28 fp=0xc00050dfe0 sp=0xc00050dfb8 pc=0x55eba00af308
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00050dfe8 sp=0xc00050dfe0 pc=0x55eb9fcf6701
created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1
	github.com/ollama/ollama/llama/runner/runner.go:975 +0xde5

goroutine 21 gp=0xc0001048c0 m=nil [IO wait]:
runtime.gopark(0x55eb9fd783e5?, 0xc000686280?, 0x10?, 0xfa?, 0xb?)
	runtime/proc.go:424 +0xce fp=0xc0000ef918 sp=0xc0000ef8f8 pc=0x55eb9fcee32e
runtime.netpollblock(0x55eb9fd116f8?, 0x9fc85146?, 0xeb?)
	runtime/netpoll.go:575 +0xf7 fp=0xc0000ef950 sp=0xc0000ef918 pc=0x55eb9fcb1f97
internal/poll.runtime_pollWait(0x7f7195653568, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc0000ef970 sp=0xc0000ef950 pc=0x55eb9fced625
internal/poll.(*pollDesc).wait(0xc000686280?, 0xc0004fc000?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000ef998 sp=0xc0000ef970 pc=0x55eb9fd74de7
internal/poll.(*pollDesc).waitRead(...)
	internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc000686280, {0xc0004fc000, 0x1000, 0x1000})
	internal/poll/fd_unix.go:165 +0x27a fp=0xc0000efa30 sp=0xc0000ef998 pc=0x55eb9fd760da
net.(*netFD).Read(0xc000686280, {0xc0004fc000?, 0xc0000efaa0?, 0x55eb9fd752a5?})
	net/fd_posix.go:55 +0x25 fp=0xc0000efa78 sp=0xc0000efa30 pc=0x55eb9fde12e5
net.(*conn).Read(0xc00007a000, {0xc0004fc000?, 0x0?, 0xc0006911d8?})
	net/net.go:189 +0x45 fp=0xc0000efac0 sp=0xc0000efa78 pc=0x55eb9fdef8e5
net.(*TCPConn).Read(0xc0006911d0?, {0xc0004fc000?, 0xc000686280?, 0xc0000efaf8?})
	<autogenerated>:1 +0x25 fp=0xc0000efaf0 sp=0xc0000efac0 pc=0x55eb9fe02ae5
net/http.(*connReader).Read(0xc0006911d0, {0xc0004fc000, 0x1000, 0x1000})
	net/http/server.go:798 +0x14b fp=0xc0000efb40 sp=0xc0000efaf0 pc=0x55eba000fd8b
bufio.(*Reader).fill(0xc000492900)
	bufio/bufio.go:110 +0x103 fp=0xc0000efb78 sp=0xc0000efb40 pc=0x55eb9fe071e3
bufio.(*Reader).Peek(0xc000492900, 0x4)
	bufio/bufio.go:148 +0x53 fp=0xc0000efb98 sp=0xc0000efb78 pc=0x55eb9fe07313
net/http.(*conn).serve(0xc000518000, {0x55eba0ebcf08, 0xc000691170})
	net/http/server.go:2127 +0x738 fp=0xc0000effb8 sp=0xc0000efb98 pc=0x55eba00150d8
net/http.(*Server).Serve.gowrap3()
	net/http/server.go:3360 +0x28 fp=0xc0000effe0 sp=0xc0000effb8 pc=0x55eba001a3c8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000effe8 sp=0xc0000effe0 pc=0x55eb9fcf6701
created by net/http.(*Server).Serve in goroutine 1
	net/http/server.go:3360 +0x485

rax    0xffffffffffffff20
rbx    0x7f7140d31730
rcx    0x3
rdx    0x7f71400513a0
rdi    0x7f7140d31730
rsi    0x3
rbp    0x0
rsp    0x7f714e5fd0d0
r8     0x0
r9     0x7f6f18e90bb8
r10    0x17
r11    0x7f714e5fcd38
r12    0x0
r13    0x7f6f18e90bb8
r14    0x1
r15    0x0
rip    0x7f7135082c2d
rflags 0x10246
cs     0x33
fs     0x0
gs     0x0
time=2025-11-13T18:37:29.113Z level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: exit status 2"
[GIN] 2025/11/13 - 18:37:29 | 500 |  1.286867048s |       127.0.0.1 | POST     "/api/generate"
<!-- gh-comment-id:3529187181 --> @Mubelotix commented on GitHub (Nov 13, 2025): I can confirm <details> <summary>Logs</summary> ```bash ansible@server:~$ sudo dmesg | grep amdgpu [ 0.000000] Command line: BOOT_IMAGE=/boot/vmlinuz-6.16.3+deb13-amd64 root=UUID=056a13c4-d1c6-4879-8008-b0bb5544c1b7 ro quiet amdgpu.virtual_display=0000:c6:00.0,1 amdgpu.gpu_recovery=1 [ 0.009612] Kernel command line: BOOT_IMAGE=/boot/vmlinuz-6.16.3+deb13-amd64 root=UUID=056a13c4-d1c6-4879-8008-b0bb5544c1b7 ro quiet amdgpu.virtual_display=0000:c6:00.0,1 amdgpu.gpu_recovery=1 [ 3.269250] [drm] amdgpu kernel modesetting enabled. [ 3.274888] amdgpu: Virtual CRAT table created for CPU [ 3.274905] amdgpu: Topology: Add CPU node [ 3.275000] amdgpu 0000:c6:00.0: enabling device (0006 -> 0007) [ 3.278571] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 0 <soc21_common> [ 3.278575] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 1 <gmc_v11_0> [ 3.278577] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 2 <ih_v6_0> [ 3.278579] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 3 <psp> [ 3.278581] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 4 <smu> [ 3.278583] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 5 <amdgpu_vkms> [ 3.278585] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 6 <gfx_v11_0> [ 3.278587] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 7 <sdma_v6_0> [ 3.278589] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 8 <vcn_v4_0> [ 3.278591] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 9 <jpeg_v4_0> [ 3.278592] amdgpu 0000:c6:00.0: amdgpu: detected ip block number 10 <mes_v11_0> [ 3.278607] amdgpu 0000:c6:00.0: amdgpu: Fetched VBIOS from VFCT [ 3.278609] amdgpu: ATOM BIOS: 113-PHXGENERIC-001 [ 3.287740] amdgpu 0000:c6:00.0: vgaarb: deactivate vga console [ 3.287745] amdgpu 0000:c6:00.0: amdgpu: Trusted Memory Zone (TMZ) feature enabled [ 3.287825] amdgpu 0000:c6:00.0: amdgpu: VRAM: 4096M 0x0000008000000000 - 0x00000080FFFFFFFF (4096M used) [ 3.287827] amdgpu 0000:c6:00.0: amdgpu: GART: 512M 0x00007FFF00000000 - 0x00007FFF1FFFFFFF [ 3.288037] [drm] amdgpu: 4096M of VRAM memory ready [ 3.288039] [drm] amdgpu: 5895M of GTT memory ready. [ 3.289553] amdgpu 0000:c6:00.0: amdgpu: Found VCN firmware Version ENC: 1.23 DEC: 9 VEP: 0 Revision: 15 [ 3.315004] amdgpu 0000:c6:00.0: amdgpu: reserve 0x4000000 from 0x80f8000000 for PSP TMR [ 3.786275] amdgpu 0000:c6:00.0: amdgpu: RAS: optional ras ta ucode is not available [ 3.794536] amdgpu 0000:c6:00.0: amdgpu: RAP: optional rap ta ucode is not available [ 3.794544] amdgpu 0000:c6:00.0: amdgpu: SECUREDISPLAY: optional securedisplay ta ucode is not available [ 3.826991] amdgpu 0000:c6:00.0: amdgpu: SMU is initialized successfully! [ 3.835317] kfd kfd: amdgpu: Allocated 3969056 bytes on gart [ 3.835334] kfd kfd: amdgpu: Total number of KFD nodes to be created: 1 [ 3.835989] amdgpu: Virtual CRAT table created for GPU [ 3.836143] amdgpu: Topology: Add dGPU node [0x1900:0x1002] [ 3.836145] kfd kfd: amdgpu: added device 1002:1900 [ 3.836157] amdgpu 0000:c6:00.0: amdgpu: SE 1, SH per SE 2, CU per SH 6, active_cu_number 12 [ 3.836163] amdgpu 0000:c6:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0 [ 3.836166] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0 [ 3.836167] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0 [ 3.836168] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0 [ 3.836170] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0 [ 3.836171] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0 [ 3.836172] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0 [ 3.836173] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0 [ 3.836175] amdgpu 0000:c6:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0 [ 3.836176] amdgpu 0000:c6:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0 [ 3.836177] amdgpu 0000:c6:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8 [ 3.836178] amdgpu 0000:c6:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8 [ 3.836180] amdgpu 0000:c6:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0 [ 3.837387] amdgpu 0000:c6:00.0: amdgpu: Runtime PM not available [ 3.837556] [drm] Initialized amdgpu 3.64.0 for 0000:c6:00.0 on minor 0 [ 3.840048] fbcon: amdgpudrmfb (fb0) is primary device [ 3.873996] amdgpu 0000:c6:00.0: [drm] fb0: amdgpudrmfb frame buffer device ansible@server:~$ sudo docker stop ollama ollama ansible@server:~$ sudo docker rm ollama ollama ansible@server:~$ sudo docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 11434:11434 --name ollama -e HSA_OVERRIDE_GFX_VERSION=11.0.0 -e HSA_ENABLE_SDMA=0 -e HCC_AMDGPU_TARGET=gfx1103_r1 ollama/ollama:rocm 7fac4a565313628f9c42e6db4ffbf625deeac3fc6a1a4f7fb725924182306dd8 ansible@server:~$ sudo docker logs ollama 2025/11/13 18:37:07 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:11.0.0 HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-11-13T18:37:07.937Z level=INFO source=images.go:432 msg="total blobs: 12" time=2025-11-13T18:37:07.937Z level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-11-13T18:37:07.938Z level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)" time=2025-11-13T18:37:07.938Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-11-13T18:37:07.939Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2025-11-13T18:37:07.939Z level=INFO source=amd_linux.go:389 msg="skipping rocm gfx compatibility check" HSA_OVERRIDE_GFX_VERSION=11.0.0 time=2025-11-13T18:37:07.939Z level=INFO source=types.go:130 msg="inference compute" id=0 library=rocm variant="" compute=gfx1103 driver=0.0 name=1002:1900 total="4.0 GiB" available="3.9 GiB" ansible@server:~$ sudo docker exec -it ollama ollama run qwen:0.5b Error: llama runner process has terminated: exit status 2 ansible@server:~$ sudo docker logs ollama 2025/11/13 18:37:07 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:11.0.0 HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-11-13T18:37:07.937Z level=INFO source=images.go:432 msg="total blobs: 12" time=2025-11-13T18:37:07.937Z level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-11-13T18:37:07.938Z level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)" time=2025-11-13T18:37:07.938Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-11-13T18:37:07.939Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2025-11-13T18:37:07.939Z level=INFO source=amd_linux.go:389 msg="skipping rocm gfx compatibility check" HSA_OVERRIDE_GFX_VERSION=11.0.0 time=2025-11-13T18:37:07.939Z level=INFO source=types.go:130 msg="inference compute" id=0 library=rocm variant="" compute=gfx1103 driver=0.0 name=1002:1900 total="4.0 GiB" available="3.9 GiB" [GIN] 2025/11/13 - 18:37:27 | 200 | 33.012µs | 127.0.0.1 | HEAD "/" [GIN] 2025/11/13 - 18:37:27 | 200 | 10.801318ms | 127.0.0.1 | POST "/api/show" time=2025-11-13T18:37:27.857Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-fad2a06e4cc705c2fa8bec5477ddb00dc0c859ac184c34dcc5586663774161ca gpu=0 parallel=4 available=4220772352 required="1.8 GiB" time=2025-11-13T18:37:27.857Z level=INFO source=server.go:100 msg="system memory" total="11.5 GiB" free="9.5 GiB" free_swap="976.0 MiB" time=2025-11-13T18:37:27.858Z level=INFO source=memory.go:356 msg="offload to rocm" layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[3.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.8 GiB" memory.required.partial="1.8 GiB" memory.required.kv="768.0 MiB" memory.required.allocations="[1.8 GiB]" memory.weights.total="933.8 MiB" memory.weights.repeating="812.1 MiB" memory.weights.nonrepeating="121.7 MiB" memory.graph.full="298.8 MiB" memory.graph.partial="420.5 MiB" time=2025-11-13T18:37:27.858Z level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-fad2a06e4cc705c2fa8bec5477ddb00dc0c859ac184c34dcc5586663774161ca --ctx-size 8192 --batch-size 512 --n-gpu-layers 25 --threads 8 --parallel 4 --port 37589" time=2025-11-13T18:37:27.859Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-11-13T18:37:27.859Z level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-11-13T18:37:27.859Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-11-13T18:37:27.867Z level=INFO source=runner.go:936 msg="starting go runner" time=2025-11-13T18:37:27.867Z level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=8 time=2025-11-13T18:37:27.867Z level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:37589" /opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory time=2025-11-13T18:37:28.111Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon Graphics, compute capability 11.0, VMM: no load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so llama_load_model_from_file: using device ROCm0 (AMD Radeon Graphics) - 5816 MiB free llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-fad2a06e4cc705c2fa8bec5477ddb00dc0c859ac184c34dcc5586663774161ca (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = qwen2 llama_model_loader: - kv 1: general.name str = Qwen2-beta-0_5B-Chat llama_model_loader: - kv 2: qwen2.block_count u32 = 24 llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 llama_model_loader: - kv 4: qwen2.embedding_length u32 = 1024 llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 2816 llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 16 llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 16 llama_model_loader: - kv 8: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 9: qwen2.use_parallel_residual bool = true llama_model_loader: - kv 10: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 11: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 12: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 13: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 14: tokenizer.ggml.eos_token_id u32 = 151643 llama_model_loader: - kv 15: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 17: tokenizer.chat_template str = {% for message in messages %}{% if lo... llama_model_loader: - kv 18: general.quantization_version u32 = 2 llama_model_loader: - kv 19: general.file_type u32 = 2 llama_model_loader: - type f32: 121 tensors llama_model_loader: - type q4_0: 169 tensors llama_model_loader: - type q6_K: 1 tensors llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default' llm_load_vocab: special tokens cache size = 293 llm_load_vocab: token to piece cache size = 0.9338 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 151936 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 1024 llm_load_print_meta: n_layer = 24 llm_load_print_meta: n_head = 16 llm_load_print_meta: n_head_kv = 16 llm_load_print_meta: n_rot = 64 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 64 llm_load_print_meta: n_embd_head_v = 64 llm_load_print_meta: n_gqa = 1 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 2816 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 2 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 10000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 32768 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 0.5B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 619.57 M llm_load_print_meta: model size = 371.02 MiB (5.02 BPW) llm_load_print_meta: general.name = Qwen2-beta-0_5B-Chat llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOT token = 151645 '<|im_end|>' llm_load_print_meta: PAD token = 151643 '<|endoftext|>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: EOG token = 151643 '<|endoftext|>' llm_load_print_meta: EOG token = 151645 '<|im_end|>' llm_load_print_meta: max token length = 256 SIGSEGV: segmentation violation PC=0x7f7135082c2d m=3 sigcode=1 addr=0x18 signal arrived during cgo execution goroutine 51 gp=0xc0005048c0 m=3 mp=0xc00007ce08 [syscall]: runtime.cgocall(0x55eba088f540, 0xc000093b78) runtime/cgocall.go:167 +0x4b fp=0xc000093b50 sp=0xc000093b18 pc=0x55eb9fce7c2b github.com/ollama/ollama/llama._Cfunc_llama_load_model_from_file(0x7f7140c6ade0, {0x0, 0x19, 0x1, 0x0, 0x0, 0x0, 0x55eba088ef50, 0xc000014088, 0x0, ...}) _cgo_gotypes.go:689 +0x50 fp=0xc000093b78 sp=0xc000093b50 pc=0x55eba009d590 github.com/ollama/ollama/llama.LoadModelFromFile.func1({0x7ffe84b23d70?, 0xc0005048c0?}, {0x0, 0x19, 0x1, 0x0, 0x0, 0x0, 0x55eba088ef50, 0xc000014088, ...}) github.com/ollama/ollama/llama/llama.go:271 +0x127 fp=0xc000093c78 sp=0xc000093b78 pc=0x55eba00a0d87 github.com/ollama/ollama/llama.LoadModelFromFile({0x7ffe84b23d70, 0x62}, {0x19, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc000117f70, ...}) github.com/ollama/ollama/llama/llama.go:271 +0x2d6 fp=0xc000093dc8 sp=0xc000093c78 pc=0x55eba00a0a76 github.com/ollama/ollama/llama/runner.(*Server).loadModel(0xc0001a9560, {0x19, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc000117f70, 0x0}, ...) github.com/ollama/ollama/llama/runner/runner.go:850 +0xb2 fp=0xc000093f10 sp=0xc000093dc8 pc=0x55eba00adab2 github.com/ollama/ollama/llama/runner.Execute.gowrap1() github.com/ollama/ollama/llama/runner/runner.go:970 +0xda fp=0xc000093fe0 sp=0xc000093f10 pc=0x55eba00af41a runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000093fe8 sp=0xc000093fe0 pc=0x55eb9fcf6701 created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1 github.com/ollama/ollama/llama/runner/runner.go:970 +0xd0d goroutine 1 gp=0xc0000061c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0005155e8 sp=0xc0005155c8 pc=0x55eb9fcee32e runtime.netpollblock(0xc000519f80?, 0x9fc85146?, 0xeb?) runtime/netpoll.go:575 +0xf7 fp=0xc000515620 sp=0xc0005155e8 pc=0x55eb9fcb1f97 internal/poll.runtime_pollWait(0x7f7195653680, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000515640 sp=0xc000515620 pc=0x55eb9fced625 internal/poll.(*pollDesc).wait(0xc0004c0f80?, 0x2c?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000515668 sp=0xc000515640 pc=0x55eb9fd74de7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0xc0004c0f80) internal/poll/fd_unix.go:620 +0x295 fp=0xc000515710 sp=0xc000515668 pc=0x55eb9fd7a1b5 net.(*netFD).accept(0xc0004c0f80) net/fd_unix.go:172 +0x29 fp=0xc0005157c8 sp=0xc000515710 pc=0x55eb9fde32a9 net.(*TCPListener).accept(0xc000122b40) net/tcpsock_posix.go:159 +0x1e fp=0xc000515818 sp=0xc0005157c8 pc=0x55eb9fdf8f1e net.(*TCPListener).Accept(0xc000122b40) net/tcpsock.go:372 +0x30 fp=0xc000515848 sp=0xc000515818 pc=0x55eb9fdf7dd0 net/http.(*onceCloseListener).Accept(0xc000518000?) <autogenerated>:1 +0x24 fp=0xc000515860 sp=0xc000515848 pc=0x55eba0042044 net/http.(*Server).Serve(0xc000146a50, {0x55eba0ebabf0, 0xc000122b40}) net/http/server.go:3330 +0x30c fp=0xc000515990 sp=0xc000515860 pc=0x55eba0019fcc github.com/ollama/ollama/llama/runner.Execute({0xc000036110?, 0x0?, 0x0?}) github.com/ollama/ollama/llama/runner/runner.go:996 +0x11a9 fp=0xc000515d30 sp=0xc000515990 pc=0x55eba00aefe9 github.com/ollama/ollama/cmd.NewCLI.func2(0xc000118f00?, {0x55eba0a7d01a?, 0x4?, 0x55eba0a7d01e?}) github.com/ollama/ollama/cmd/cmd.go:1277 +0x45 fp=0xc000515d58 sp=0xc000515d30 pc=0x55eba088e905 github.com/spf13/cobra.(*Command).execute(0xc0004e7b08, {0xc0001337a0, 0xe, 0xe}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x862 fp=0xc000515e78 sp=0xc000515d58 pc=0x55eb9fe5bfe2 github.com/spf13/cobra.(*Command).ExecuteC(0xc00046db08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000515f30 sp=0xc000515e78 pc=0x55eb9fe5c825 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=0xc000515f50 sp=0xc000515f30 pc=0x55eba088ec8d runtime.main() runtime/proc.go:272 +0x29d fp=0xc000515fe0 sp=0xc000515f50 pc=0x55eb9fcb963d runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000515fe8 sp=0xc000515fe0 pc=0x55eb9fcf6701 goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000084fa8 sp=0xc000084f88 pc=0x55eb9fcee32e runtime.goparkunlock(...) runtime/proc.go:430 runtime.forcegchelper() runtime/proc.go:337 +0xb8 fp=0xc000084fe0 sp=0xc000084fa8 pc=0x55eb9fcb9978 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000084fe8 sp=0xc000084fe0 pc=0x55eb9fcf6701 created by runtime.init.7 in goroutine 1 runtime/proc.go:325 +0x1a goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000085780 sp=0xc000085760 pc=0x55eb9fcee32e runtime.goparkunlock(...) runtime/proc.go:430 runtime.bgsweep(0xc00003e080) runtime/mgcsweep.go:317 +0xdf fp=0xc0000857c8 sp=0xc000085780 pc=0x55eb9fca401f runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc0000857e0 sp=0xc0000857c8 pc=0x55eb9fc98665 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000857e8 sp=0xc0000857e0 pc=0x55eb9fcf6701 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x55eba0c23c48?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x55eb9fcee32e runtime.goparkunlock(...) runtime/proc.go:430 runtime.(*scavengerState).park(0x55eba1669820) runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x55eb9fca19e9 runtime.bgscavenge(0xc00003e080) runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x55eb9fca1f79 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x55eb9fc98605 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x55eb9fcf6701 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]: runtime.gopark(0xc000084648?, 0x55eb9fc8eb65?, 0xb0?, 0x1?, 0xc0000061c0?) runtime/proc.go:424 +0xce fp=0xc000084620 sp=0xc000084600 pc=0x55eb9fcee32e runtime.runfinq() runtime/mfinal.go:193 +0x107 fp=0xc0000847e0 sp=0xc000084620 pc=0x55eb9fc976e7 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000847e8 sp=0xc0000847e0 pc=0x55eb9fcf6701 created by runtime.createfing in goroutine 1 runtime/mfinal.go:163 +0x3d goroutine 6 gp=0xc0001c7500 m=nil [chan receive]: runtime.gopark(0xc000086760?, 0x55eb9fdca925?, 0x70?, 0x8?, 0x55eba0ece880?) runtime/proc.go:424 +0xce fp=0xc000086718 sp=0xc0000866f8 pc=0x55eb9fcee32e runtime.chanrecv(0xc0000b8310, 0x0, 0x1) runtime/chan.go:639 +0x41c fp=0xc000086790 sp=0xc000086718 pc=0x55eb9fc87d5c runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:489 +0x12 fp=0xc0000867b8 sp=0xc000086790 pc=0x55eb9fc87912 runtime.unique_runtime_registerUniqueMapCleanup.func1(...) runtime/mgc.go:1781 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1784 +0x2f fp=0xc0000867e0 sp=0xc0000867b8 pc=0x55eb9fc9b6cf runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000867e8 sp=0xc0000867e0 pc=0x55eb9fcf6701 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1779 +0x96 goroutine 7 gp=0xc0001c7dc0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000086f38 sp=0xc000086f18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc000086fc8 sp=0xc000086f38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000086fe0 sp=0xc000086fc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000086fe8 sp=0xc000086fe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 8 gp=0xc0004a4000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000087738 sp=0xc000087718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000877c8 sp=0xc000087738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000877e0 sp=0xc0000877c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000877e8 sp=0xc0000877e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 9 gp=0xc0004a41c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000087f38 sp=0xc000087f18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc000087fc8 sp=0xc000087f38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000087fe0 sp=0xc000087fc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 10 gp=0xc0004a4380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000080738 sp=0xc000080718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000807c8 sp=0xc000080738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000807e0 sp=0xc0000807c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000807e8 sp=0xc0000807e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 11 gp=0xc0004a4540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000080f38 sp=0xc000080f18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc000080fc8 sp=0xc000080f38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000080fe0 sp=0xc000080fc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 12 gp=0xc0004a4700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000081738 sp=0xc000081718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000817c8 sp=0xc000081738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000817e0 sp=0xc0000817c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000817e8 sp=0xc0000817e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 13 gp=0xc0004a48c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000081f38 sp=0xc000081f18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc000081fc8 sp=0xc000081f38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000081fe0 sp=0xc000081fc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 14 gp=0xc0004a4a80 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000082738 sp=0xc000082718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000827c8 sp=0xc000082738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000827e0 sp=0xc0000827c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000827e8 sp=0xc0000827e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 18 gp=0xc000504000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 34 gp=0xc000104380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 15 gp=0xc0004a4c40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000082f38 sp=0xc000082f18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc000082fc8 sp=0xc000082f38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000082fe0 sp=0xc000082fc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000082fe8 sp=0xc000082fe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 35 gp=0xc000104540 m=nil [GC worker (idle)]: runtime.gopark(0x189afdba467?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000506f38 sp=0xc000506f18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc000506fc8 sp=0xc000506f38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000506fe0 sp=0xc000506fc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000506fe8 sp=0xc000506fe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 16 gp=0xc0004a4e00 m=nil [GC worker (idle)]: runtime.gopark(0x55eba1717e80?, 0x1?, 0x5d?, 0xba?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000083738 sp=0xc000083718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000837c8 sp=0xc000083738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000837e0 sp=0xc0000837c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000837e8 sp=0xc0000837e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 19 gp=0xc0005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x55eba1717e80?, 0x1?, 0x84?, 0x5c?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 50 gp=0xc0004a4fc0 m=nil [GC worker (idle)]: runtime.gopark(0x55eba1717e80?, 0x1?, 0x1?, 0xd?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000083f38 sp=0xc000083f18 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc000083fc8 sp=0xc000083f38 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000083fe0 sp=0xc000083fc8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000083fe8 sp=0xc000083fe0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 20 gp=0xc000504380 m=nil [GC worker (idle)]: runtime.gopark(0x55eba1717e80?, 0x1?, 0x77?, 0xbc?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x55eb9fcee32e runtime.gcBgMarkWorker(0xc0000b98f0) runtime/mgc.go:1412 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x55eb9fc9a9c9 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x55eb9fc9a8a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x55eb9fcf6701 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 52 gp=0xc000504a80 m=nil [semacquire]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00050de18 sp=0xc00050ddf8 pc=0x55eb9fcee32e runtime.goparkunlock(...) runtime/proc.go:430 runtime.semacquire1(0xc0001a9568, 0x0, 0x1, 0x0, 0x12) runtime/sema.go:178 +0x22c fp=0xc00050de80 sp=0xc00050de18 pc=0x55eb9fccc6ec sync.runtime_Semacquire(0x0?) runtime/sema.go:71 +0x25 fp=0xc00050deb8 sp=0xc00050de80 pc=0x55eb9fcefb45 sync.(*WaitGroup).Wait(0x0?) sync/waitgroup.go:118 +0x48 fp=0xc00050dee0 sp=0xc00050deb8 pc=0x55eb9fd04f28 github.com/ollama/ollama/llama/runner.(*Server).run(0xc0001a9560, {0x55eba0ebcf40, 0xc000127540}) github.com/ollama/ollama/llama/runner/runner.go:315 +0x47 fp=0xc00050dfb8 sp=0xc00050dee0 pc=0x55eba00aa287 github.com/ollama/ollama/llama/runner.Execute.gowrap2() github.com/ollama/ollama/llama/runner/runner.go:975 +0x28 fp=0xc00050dfe0 sp=0xc00050dfb8 pc=0x55eba00af308 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050dfe8 sp=0xc00050dfe0 pc=0x55eb9fcf6701 created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1 github.com/ollama/ollama/llama/runner/runner.go:975 +0xde5 goroutine 21 gp=0xc0001048c0 m=nil [IO wait]: runtime.gopark(0x55eb9fd783e5?, 0xc000686280?, 0x10?, 0xfa?, 0xb?) runtime/proc.go:424 +0xce fp=0xc0000ef918 sp=0xc0000ef8f8 pc=0x55eb9fcee32e runtime.netpollblock(0x55eb9fd116f8?, 0x9fc85146?, 0xeb?) runtime/netpoll.go:575 +0xf7 fp=0xc0000ef950 sp=0xc0000ef918 pc=0x55eb9fcb1f97 internal/poll.runtime_pollWait(0x7f7195653568, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0000ef970 sp=0xc0000ef950 pc=0x55eb9fced625 internal/poll.(*pollDesc).wait(0xc000686280?, 0xc0004fc000?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000ef998 sp=0xc0000ef970 pc=0x55eb9fd74de7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0xc000686280, {0xc0004fc000, 0x1000, 0x1000}) internal/poll/fd_unix.go:165 +0x27a fp=0xc0000efa30 sp=0xc0000ef998 pc=0x55eb9fd760da net.(*netFD).Read(0xc000686280, {0xc0004fc000?, 0xc0000efaa0?, 0x55eb9fd752a5?}) net/fd_posix.go:55 +0x25 fp=0xc0000efa78 sp=0xc0000efa30 pc=0x55eb9fde12e5 net.(*conn).Read(0xc00007a000, {0xc0004fc000?, 0x0?, 0xc0006911d8?}) net/net.go:189 +0x45 fp=0xc0000efac0 sp=0xc0000efa78 pc=0x55eb9fdef8e5 net.(*TCPConn).Read(0xc0006911d0?, {0xc0004fc000?, 0xc000686280?, 0xc0000efaf8?}) <autogenerated>:1 +0x25 fp=0xc0000efaf0 sp=0xc0000efac0 pc=0x55eb9fe02ae5 net/http.(*connReader).Read(0xc0006911d0, {0xc0004fc000, 0x1000, 0x1000}) net/http/server.go:798 +0x14b fp=0xc0000efb40 sp=0xc0000efaf0 pc=0x55eba000fd8b bufio.(*Reader).fill(0xc000492900) bufio/bufio.go:110 +0x103 fp=0xc0000efb78 sp=0xc0000efb40 pc=0x55eb9fe071e3 bufio.(*Reader).Peek(0xc000492900, 0x4) bufio/bufio.go:148 +0x53 fp=0xc0000efb98 sp=0xc0000efb78 pc=0x55eb9fe07313 net/http.(*conn).serve(0xc000518000, {0x55eba0ebcf08, 0xc000691170}) net/http/server.go:2127 +0x738 fp=0xc0000effb8 sp=0xc0000efb98 pc=0x55eba00150d8 net/http.(*Server).Serve.gowrap3() net/http/server.go:3360 +0x28 fp=0xc0000effe0 sp=0xc0000effb8 pc=0x55eba001a3c8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000effe8 sp=0xc0000effe0 pc=0x55eb9fcf6701 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3360 +0x485 rax 0xffffffffffffff20 rbx 0x7f7140d31730 rcx 0x3 rdx 0x7f71400513a0 rdi 0x7f7140d31730 rsi 0x3 rbp 0x0 rsp 0x7f714e5fd0d0 r8 0x0 r9 0x7f6f18e90bb8 r10 0x17 r11 0x7f714e5fcd38 r12 0x0 r13 0x7f6f18e90bb8 r14 0x1 r15 0x0 rip 0x7f7135082c2d rflags 0x10246 cs 0x33 fs 0x0 gs 0x0 time=2025-11-13T18:37:29.113Z level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: exit status 2" [GIN] 2025/11/13 - 18:37:29 | 500 | 1.286867048s | 127.0.0.1 | POST "/api/generate" ``` </details>
GiteaMirror commented 2026-05-04 20:45:36 -05:00
Author
Owner
Copy Link

@Mubelotix commented on GitHub (Nov 13, 2025):

I worked around the issue

https://github.com/ollama/ollama/issues/8262

<!-- gh-comment-id:3529206558 --> @Mubelotix commented on GitHub (Nov 13, 2025): I worked around the issue https://github.com/ollama/ollama/issues/8262
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#70240
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?