github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 22:21:55 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8108] Error: llama runner process has terminated: error:/opt/rocm/lib/libhipblas.so.2: undefined symbol: rocblas_sgbmv_64 #5183

New Issue
Open
opened 2026-04-12 16:18:48 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 16:18:48 -05:00
Owner
Copy Link

Originally created by @dernikolas on GitHub (Dec 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8108

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

When I start llama3.2 with ollama run llama3.2 this error spawns:
Error: llama runner process has terminated: error:/opt/rocm/lib/libhipblas.so.2: undefined symbol: rocblas_sgbmv_64

I am on Cachy OS with ollama and ollama-rocm installed from extra repo and a AMD RX6800 is the GPU

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.5.2

Originally created by @dernikolas on GitHub (Dec 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8108 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? When I start llama3.2 with `ollama run llama3.2` this error spawns: `Error: llama runner process has terminated: error:/opt/rocm/lib/libhipblas.so.2: undefined symbol: rocblas_sgbmv_64` I am on Cachy OS with ollama and ollama-rocm installed from extra repo and a AMD RX6800 is the GPU ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.5.2
GiteaMirror added the linuxamdneeds more infobug labels 2026-04-12 16:18:48 -05:00
GiteaMirror commented 2026-04-12 16:18:49 -05:00
Author
Owner
Copy Link

@dernikolas commented on GitHub (Dec 19, 2024):

This is the entire Output of ollama serve

2024/12/19 14:32:08 routes.go:1259: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/nikolas/.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=2024-12-19T14:32:08.393+01:00 level=INFO source=images.go:757 msg="total blobs: 6"
time=2024-12-19T14:32:08.393+01:00 level=INFO source=images.go:764 msg="total unused blobs removed: 0"
time=2024-12-19T14:32:08.393+01:00 level=INFO source=routes.go:1310 msg="Listening on 127.0.0.1:11434 (version 0.5.4)"
time=2024-12-19T14:32:08.393+01:00 level=INFO source=routes.go:1339 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 rocm_avx]"
time=2024-12-19T14:32:08.393+01:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs"
time=2024-12-19T14:32:08.414+01:00 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=2024-12-19T14:32:08.422+01:00 level=INFO source=amd_linux.go:388 msg="amdgpu is supported" gpu=GPU-19bef92a6afb854a gpu_type=gfx1030
time=2024-12-19T14:32:08.422+01:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-19bef92a6afb854a library=rocm variant="" compute=gfx1030 driver=0.0 name=1002:73bf total="16.0 GiB" available="14.7 GiB"
[GIN] 2024/12/19 - 14:32:19 | 200 |      28.137µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/12/19 - 14:32:19 | 200 |   19.078344ms |       127.0.0.1 | POST     "/api/show"
time=2024-12-19T14:32:19.832+01:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/home/nikolas/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-19bef92a6afb854a parallel=4 available=15836614656 required="3.7 GiB"
time=2024-12-19T14:32:19.832+01:00 level=INFO source=server.go:104 msg="system memory" total="31.0 GiB" free="25.0 GiB" free_swap="4.0 GiB"
time=2024-12-19T14:32:19.833+01:00 level=INFO source=memory.go:356 msg="offload to rocm" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[14.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weights.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB"
time=2024-12-19T14:32:19.834+01:00 level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/rocm_avx/ollama_llama_server runner --model /home/nikolas/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 43265"
time=2024-12-19T14:32:19.834+01:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-19T14:32:19.834+01:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding"
time=2024-12-19T14:32:19.834+01:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error"
/usr/lib/ollama/runners/rocm_avx/ollama_llama_server: symbol lookup error: /opt/rocm/lib/libhipblas.so.2: undefined symbol: rocblas_sgbmv_64
time=2024-12-19T14:32:20.085+01:00 level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: error:/opt/rocm/lib/libhipblas.so.2: undefined symbol: rocblas_sgbmv_64"
[GIN] 2024/12/19 - 14:32:20 | 500 |  286.816521ms |       127.0.0.1 | POST     "/api/generate"
<!-- gh-comment-id:2554007459 --> @dernikolas commented on GitHub (Dec 19, 2024): This is the entire Output of `ollama serve` ``` 2024/12/19 14:32:08 routes.go:1259: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/nikolas/.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=2024-12-19T14:32:08.393+01:00 level=INFO source=images.go:757 msg="total blobs: 6" time=2024-12-19T14:32:08.393+01:00 level=INFO source=images.go:764 msg="total unused blobs removed: 0" time=2024-12-19T14:32:08.393+01:00 level=INFO source=routes.go:1310 msg="Listening on 127.0.0.1:11434 (version 0.5.4)" time=2024-12-19T14:32:08.393+01:00 level=INFO source=routes.go:1339 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 rocm_avx]" time=2024-12-19T14:32:08.393+01:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2024-12-19T14:32:08.414+01:00 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=2024-12-19T14:32:08.422+01:00 level=INFO source=amd_linux.go:388 msg="amdgpu is supported" gpu=GPU-19bef92a6afb854a gpu_type=gfx1030 time=2024-12-19T14:32:08.422+01:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-19bef92a6afb854a library=rocm variant="" compute=gfx1030 driver=0.0 name=1002:73bf total="16.0 GiB" available="14.7 GiB" [GIN] 2024/12/19 - 14:32:19 | 200 | 28.137µs | 127.0.0.1 | HEAD "/" [GIN] 2024/12/19 - 14:32:19 | 200 | 19.078344ms | 127.0.0.1 | POST "/api/show" time=2024-12-19T14:32:19.832+01:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/home/nikolas/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-19bef92a6afb854a parallel=4 available=15836614656 required="3.7 GiB" time=2024-12-19T14:32:19.832+01:00 level=INFO source=server.go:104 msg="system memory" total="31.0 GiB" free="25.0 GiB" free_swap="4.0 GiB" time=2024-12-19T14:32:19.833+01:00 level=INFO source=memory.go:356 msg="offload to rocm" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[14.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weights.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB" time=2024-12-19T14:32:19.834+01:00 level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/rocm_avx/ollama_llama_server runner --model /home/nikolas/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 43265" time=2024-12-19T14:32:19.834+01:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2024-12-19T14:32:19.834+01:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding" time=2024-12-19T14:32:19.834+01:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error" /usr/lib/ollama/runners/rocm_avx/ollama_llama_server: symbol lookup error: /opt/rocm/lib/libhipblas.so.2: undefined symbol: rocblas_sgbmv_64 time=2024-12-19T14:32:20.085+01:00 level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: error:/opt/rocm/lib/libhipblas.so.2: undefined symbol: rocblas_sgbmv_64" [GIN] 2024/12/19 - 14:32:20 | 500 | 286.816521ms | 127.0.0.1 | POST "/api/generate" ```
GiteaMirror commented 2026-04-12 16:18:49 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 6, 2025):

with ollama and ollama-rocm installed from extra repo

It sounds like this was a binary install from a repo that the Ollama maintainers don't manage or control, and the binaries in that repo were linked against a different ROCm version that isn't compatible with the one you have installed.

Your best bet may be to follow the https://github.com/ollama/ollama/blob/main/docs/linux.md#manual-install instructions. Alternatively if you can figure out which ROCm version your packaged Ollama was compiled against, install that version and it should resolve the failure.

<!-- gh-comment-id:2573620044 --> @dhiltgen commented on GitHub (Jan 6, 2025): > with ollama and ollama-rocm installed from extra repo It sounds like this was a binary install from a repo that the Ollama maintainers don't manage or control, and the binaries in that repo were linked against a different ROCm version that isn't compatible with the one you have installed. Your best bet may be to follow the https://github.com/ollama/ollama/blob/main/docs/linux.md#manual-install instructions. Alternatively if you can figure out which ROCm version your packaged Ollama was compiled against, install that version and it should resolve the failure.
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 amd bug linux needs more info
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#5183
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?