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

[GH-ISSUE #6165] No devices found using AMD gpus #3852

New Issue
Closed
opened 2026-04-12 14:41:31 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 14:41:31 -05:00
Owner
Copy Link

Originally created by @cinglish on GitHub (Aug 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6165

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Getting the following error when loading models with AMD gpus (Instinct MI60s):

rocBLAS error: Could not initialize Tensile host: No devices found

I have 4 devices allocated to the container and it seems to still discover them at startup:

time=2024-08-04T22:17:48.256Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-08-04T22:17:48.264Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=0 gpu_type=gfx906
time=2024-08-04T22:17:48.264Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=1
time=2024-08-04T22:17:48.264Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=2
time=2024-08-04T22:17:48.264Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=3
time=2024-08-04T22:17:48.265Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=4
time=2024-08-04T22:17:48.265Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=5 gpu_type=gfx906
time=2024-08-04T22:17:48.266Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=6 gpu_type=gfx906
time=2024-08-04T22:17:48.268Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=7 gpu_type=gfx906

It is working fine with the 0.3.1-rocm image, but seeing this behavior in the newest versions.

OS

Docker

GPU

AMD

CPU

Intel

Ollama version

0.3.2

Originally created by @cinglish on GitHub (Aug 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6165 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Getting the following error when loading models with AMD gpus (Instinct MI60s): ``` rocBLAS error: Could not initialize Tensile host: No devices found ``` I have 4 devices allocated to the container and it seems to still discover them at startup: ``` time=2024-08-04T22:17:48.256Z level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-08-04T22:17:48.264Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=0 gpu_type=gfx906 time=2024-08-04T22:17:48.264Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=1 time=2024-08-04T22:17:48.264Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=2 time=2024-08-04T22:17:48.264Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=3 time=2024-08-04T22:17:48.265Z level=WARN source=amd_linux.go:201 msg="amdgpu too old gfx000" gpu=4 time=2024-08-04T22:17:48.265Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=5 gpu_type=gfx906 time=2024-08-04T22:17:48.266Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=6 gpu_type=gfx906 time=2024-08-04T22:17:48.268Z level=INFO source=amd_linux.go:345 msg="amdgpu is supported" gpu=7 gpu_type=gfx906 ``` It is working fine with the `0.3.1-rocm` image, but seeing this behavior in the newest versions. ### OS Docker ### GPU AMD ### CPU Intel ### Ollama version 0.3.2
GiteaMirror added the dockerlinuxamdbug labels 2026-04-12 14:41:31 -05:00
GiteaMirror commented 2026-04-12 14:41:32 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Aug 9, 2024):

Can you run the container with -e OLLAMA_DEBUG=1 and share the more complete log of startup and attempting to load a model?

<!-- gh-comment-id:2278726554 --> @dhiltgen commented on GitHub (Aug 9, 2024): Can you run the container with `-e OLLAMA_DEBUG=1` and share the more complete log of startup and attempting to load a model?
GiteaMirror commented 2026-04-12 14:41:33 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 5, 2024):

If you're still having trouble, please make sure you pull the latest image, and if that doesn't resolve it, please share a more complete log as requested above and I'll reopen the issue.

<!-- gh-comment-id:2332444060 --> @dhiltgen commented on GitHub (Sep 5, 2024): If you're still having trouble, please make sure you pull the latest image, and if that doesn't resolve it, please share a more complete log as requested above and I'll reopen the issue.
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 docker linux
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#3852
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?