github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7320] 0.4.0 regression #51162

New Issue
Closed
opened 2026-04-28 18:45:01 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 18:45:01 -05:00
Owner
Copy Link

Originally created by @skobkin on GitHub (Oct 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7320

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Just updated ollama to 0.4.0-rc3-rocm to test new LLaMA 3.2 Vision capabilities.

But it isn't working and returning 500 to OpenWebUI. It isn't working even with LLaMA 3.1 Lexi which I was using before update.

image

Here's ollama container logs when trying to chat with LLaMA 3.1 Lexi 8B Q6:

ollama  | time=2024-10-22T16:33:28.879Z level=INFO source=images.go:754 msg="total blobs: 84"
ollama  | time=2024-10-22T16:33:28.880Z level=INFO source=images.go:761 msg="total unused blobs removed: 0"
ollama  | time=2024-10-22T16:33:28.880Z level=INFO source=routes.go:1217 msg="Listening on [::]:11434 (version 0.4.0-rc3)"
ollama  | time=2024-10-22T16:33:28.880Z level=INFO source=common.go:82 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 rocm]"
ollama  | time=2024-10-22T16:33:28.880Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
ollama  | time=2024-10-22T16:33:28.882Z 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"
ollama  | time=2024-10-22T16:33:28.884Z level=INFO source=amd_linux.go:383 msg="amdgpu is supported" gpu=0 gpu_type=gfx1101
ollama  | time=2024-10-22T16:33:28.884Z level=INFO source=amd_linux.go:296 msg="unsupported Radeon iGPU detected skipping" id=1 total="512.0 MiB"
ollama  | time=2024-10-22T16:33:28.884Z level=INFO source=types.go:123 msg="inference compute" id=0 library=rocm variant="" compute=gfx1101 driver=0.0 name=1002:747e total="16.0 GiB" available="15.2 GiB"
ollama  | [GIN] 2024/10/22 - 16:33:39 | 200 |     1.70353ms |      172.24.0.3 | GET      "/api/tags"
ollama  | [GIN] 2024/10/22 - 16:33:43 | 200 |      21.159µs |      172.24.0.1 | GET      "/"
ollama  | time=2024-10-22T16:33:52.469Z level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-545ba086eb5179e8f97f9eb7d54c61555a7cd645c5b26f9551209022878abb2c gpu=0 parallel=4 available=16308183040 required="9.7 GiB"
ollama  | time=2024-10-22T16:33:52.469Z level=INFO source=llama-server.go:72 msg="system memory" total="30.5 GiB" free="24.8 GiB" free_swap="7.8 GiB"
ollama  | time=2024-10-22T16:33:52.469Z level=INFO source=memory.go:346 msg="offload to rocm" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[15.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.7 GiB" memory.required.partial="9.7 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[9.7 GiB]" memory.weights.total="7.9 GiB" memory.weights.repeating="7.4 GiB" memory.weights.nonrepeating="532.3 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB"
ollama  | time=2024-10-22T16:33:52.470Z level=INFO source=llama-server.go:355 msg="starting llama server" cmd="/usr/lib/ollama/runners/rocm/ollama_llama_server --model /root/.ollama/models/blobs/sha256-545ba086eb5179e8f97f9eb7d54c61555a7cd645c5b26f9551209022878abb2c --ctx-size 8192 --batch-size 512 --embedding --n-gpu-layers 33 --threads 12 --parallel 4 --port 34353"
ollama  | time=2024-10-22T16:33:52.470Z level=INFO source=sched.go:450 msg="loaded runners" count=1
ollama  | time=2024-10-22T16:33:52.470Z level=INFO source=llama-server.go:534 msg="waiting for llama runner to start responding"
ollama  | time=2024-10-22T16:33:52.470Z level=INFO source=llama-server.go:568 msg="waiting for server to become available" status="llm server error"
ollama  | /usr/lib/ollama/runners/rocm/ollama_llama_server: error while loading shared libraries: libelf.so.1: cannot open shared object file: No such file or directory
ollama  | time=2024-10-22T16:33:52.720Z level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: exit status 127"

Just in case: I have one integrated GPU and one additional GPU in PCI-e slot.

I called this regression because it didn't work even on previously perfectly functioning model, not only on LLaMA 3.2.

It looks like it's similar to #7279, but I'm not sure, as the output isn't completely identical.

OS

Linux, Docker

GPU

AMD

CPU

AMD

Ollama version

0.4.0-rc3

Originally created by @skobkin on GitHub (Oct 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7320 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Just updated ollama to [`0.4.0-rc3-rocm`](https://hub.docker.com/layers/ollama/ollama/0.4.0-rc3/images/sha256-6b75f17d6160b28dec8d8d519ceec02dfdae20e1c2451db34f3a3351f5de373a?context=explore) to test new LLaMA 3.2 Vision capabilities. But it isn't working and returning 500 to OpenWebUI. It isn't working even with LLaMA 3.1 Lexi which I was using before update. ![image](https://github.com/user-attachments/assets/9c4a002e-98c7-47af-b2ef-2405da33c559) Here's `ollama` container logs when trying to chat with LLaMA 3.1 Lexi 8B Q6: ``` ollama | time=2024-10-22T16:33:28.879Z level=INFO source=images.go:754 msg="total blobs: 84" ollama | time=2024-10-22T16:33:28.880Z level=INFO source=images.go:761 msg="total unused blobs removed: 0" ollama | time=2024-10-22T16:33:28.880Z level=INFO source=routes.go:1217 msg="Listening on [::]:11434 (version 0.4.0-rc3)" ollama | time=2024-10-22T16:33:28.880Z level=INFO source=common.go:82 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 rocm]" ollama | time=2024-10-22T16:33:28.880Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs" ollama | time=2024-10-22T16:33:28.882Z 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" ollama | time=2024-10-22T16:33:28.884Z level=INFO source=amd_linux.go:383 msg="amdgpu is supported" gpu=0 gpu_type=gfx1101 ollama | time=2024-10-22T16:33:28.884Z level=INFO source=amd_linux.go:296 msg="unsupported Radeon iGPU detected skipping" id=1 total="512.0 MiB" ollama | time=2024-10-22T16:33:28.884Z level=INFO source=types.go:123 msg="inference compute" id=0 library=rocm variant="" compute=gfx1101 driver=0.0 name=1002:747e total="16.0 GiB" available="15.2 GiB" ollama | [GIN] 2024/10/22 - 16:33:39 | 200 | 1.70353ms | 172.24.0.3 | GET "/api/tags" ollama | [GIN] 2024/10/22 - 16:33:43 | 200 | 21.159µs | 172.24.0.1 | GET "/" ollama | time=2024-10-22T16:33:52.469Z level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-545ba086eb5179e8f97f9eb7d54c61555a7cd645c5b26f9551209022878abb2c gpu=0 parallel=4 available=16308183040 required="9.7 GiB" ollama | time=2024-10-22T16:33:52.469Z level=INFO source=llama-server.go:72 msg="system memory" total="30.5 GiB" free="24.8 GiB" free_swap="7.8 GiB" ollama | time=2024-10-22T16:33:52.469Z level=INFO source=memory.go:346 msg="offload to rocm" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[15.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="9.7 GiB" memory.required.partial="9.7 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[9.7 GiB]" memory.weights.total="7.9 GiB" memory.weights.repeating="7.4 GiB" memory.weights.nonrepeating="532.3 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB" ollama | time=2024-10-22T16:33:52.470Z level=INFO source=llama-server.go:355 msg="starting llama server" cmd="/usr/lib/ollama/runners/rocm/ollama_llama_server --model /root/.ollama/models/blobs/sha256-545ba086eb5179e8f97f9eb7d54c61555a7cd645c5b26f9551209022878abb2c --ctx-size 8192 --batch-size 512 --embedding --n-gpu-layers 33 --threads 12 --parallel 4 --port 34353" ollama | time=2024-10-22T16:33:52.470Z level=INFO source=sched.go:450 msg="loaded runners" count=1 ollama | time=2024-10-22T16:33:52.470Z level=INFO source=llama-server.go:534 msg="waiting for llama runner to start responding" ollama | time=2024-10-22T16:33:52.470Z level=INFO source=llama-server.go:568 msg="waiting for server to become available" status="llm server error" ollama | /usr/lib/ollama/runners/rocm/ollama_llama_server: error while loading shared libraries: libelf.so.1: cannot open shared object file: No such file or directory ollama | time=2024-10-22T16:33:52.720Z level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: exit status 127" ``` Just in case: I have one integrated GPU and one additional GPU in PCI-e slot. I called this regression because it didn't work even on previously perfectly functioning model, not only on LLaMA 3.2. It looks like it's similar to #7279, but I'm not sure, as the output isn't completely identical. ### OS Linux, Docker ### GPU AMD ### CPU AMD ### Ollama version 0.4.0-rc3
GiteaMirror added the bug label 2026-04-28 18:45:01 -05:00
GiteaMirror added the amd label 2026-04-28 18:48:07 -05:00
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
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#51162
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?