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 #7279] Ollama Docker image 0.4.0-rc3-rocm crashes due to missing shared library #4625

New Issue
Closed
opened 2026-04-12 15:32:15 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 15:32:15 -05:00
Owner
Copy Link

Originally created by @ic4-y on GitHub (Oct 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7279

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I just tried out the latest 0.4.0-rc3-rocm docker image and the ollama_llama_server crashes with

ollama-rocm | /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

I am running this on a Radeon Pro W6800, the latest stable release 0.3.13-rocm works just fine.

Here is a slightly bigger section of the debug log in case that is helpful.

ollama-rocm | time=2024-10-20T17:07:58.034Z 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/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --embedding --n-gpu-layers 33 --verbose --threads 12 --parallel 4 --port 46723"
ollama-rocm | time=2024-10-20T17:07:58.034Z level=DEBUG source=llama-server.go:372 msg=subprocess environment="[PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin HSA_OVERRIDE_GFX_VERSION=10.3.0 ROCR_VISIBLE_DEVICES=0 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/runners/rocm HIP_VISIBLE_DEVICES=0]"
ollama-rocm | time=2024-10-20T17:07:58.037Z level=INFO source=sched.go:450 msg="loaded runners" count=1
ollama-rocm | time=2024-10-20T17:07:58.037Z level=INFO source=llama-server.go:534 msg="waiting for llama runner to start responding"
ollama-rocm | time=2024-10-20T17:07:58.037Z level=INFO source=llama-server.go:568 msg="waiting for server to become available" status="llm server error"
ollama-rocm | /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-rocm | time=2024-10-20T17:07:58.288Z level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: exit status 127"
ollama-rocm | time=2024-10-20T17:07:58.288Z level=DEBUG source=sched.go:459 msg="triggering expiration for failed load" model=/root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa
ollama-rocm | time=2024-10-20T17:07:58.288Z level=DEBUG source=sched.go:361 msg="runner expired event received" modelPath=/root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa
ollama-rocm | time=2024-10-20T17:07:58.288Z level=DEBUG source=sched.go:376 msg="got lock to unload" modelPath=/root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa
ollama-rocm | [GIN] 2024/10/20 - 17:07:58 | 500 |  311.617978ms |       127.0.0.1 | POST     "/api/generate"

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.4.0-rc3-rocm (Docker image)

Originally created by @ic4-y on GitHub (Oct 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7279 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I just tried out the latest 0.4.0-rc3-rocm docker image and the `ollama_llama_server` crashes with ```ollama-rocm | /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``` I am running this on a Radeon Pro W6800, the latest stable release `0.3.13-rocm` works just fine. Here is a slightly bigger section of the debug log in case that is helpful. ``` ollama-rocm | time=2024-10-20T17:07:58.034Z 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/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --embedding --n-gpu-layers 33 --verbose --threads 12 --parallel 4 --port 46723" ollama-rocm | time=2024-10-20T17:07:58.034Z level=DEBUG source=llama-server.go:372 msg=subprocess environment="[PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin HSA_OVERRIDE_GFX_VERSION=10.3.0 ROCR_VISIBLE_DEVICES=0 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/runners/rocm HIP_VISIBLE_DEVICES=0]" ollama-rocm | time=2024-10-20T17:07:58.037Z level=INFO source=sched.go:450 msg="loaded runners" count=1 ollama-rocm | time=2024-10-20T17:07:58.037Z level=INFO source=llama-server.go:534 msg="waiting for llama runner to start responding" ollama-rocm | time=2024-10-20T17:07:58.037Z level=INFO source=llama-server.go:568 msg="waiting for server to become available" status="llm server error" ollama-rocm | /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-rocm | time=2024-10-20T17:07:58.288Z level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: exit status 127" ollama-rocm | time=2024-10-20T17:07:58.288Z level=DEBUG source=sched.go:459 msg="triggering expiration for failed load" model=/root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa ollama-rocm | time=2024-10-20T17:07:58.288Z level=DEBUG source=sched.go:361 msg="runner expired event received" modelPath=/root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa ollama-rocm | time=2024-10-20T17:07:58.288Z level=DEBUG source=sched.go:376 msg="got lock to unload" modelPath=/root/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa ollama-rocm | [GIN] 2024/10/20 - 17:07:58 | 500 | 311.617978ms | 127.0.0.1 | POST "/api/generate" ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.4.0-rc3-rocm (Docker image)
GiteaMirror added the dockerbug labels 2026-04-12 15:32:15 -05:00
GiteaMirror commented 2026-04-12 15:32:16 -05:00
Author
Owner
Copy Link

@robbiemu commented on GitHub (Oct 20, 2024):

check if libelf.so.1 ispresent on your Linux machine (it is usually cated in /usr/lib or /usr/lib64). if it is not present, install libutils package

<!-- gh-comment-id:2425136500 --> @robbiemu commented on GitHub (Oct 20, 2024): check if libelf.so.1 ispresent on your Linux machine (it is usually cated in /usr/lib or /usr/lib64). if it is not present, install libutils package
GiteaMirror commented 2026-04-12 15:32:16 -05:00
Author
Owner
Copy Link

@ic4-y commented on GitHub (Oct 20, 2024):

I am running this in docker. Maybe I am missing something, but why would it matter if my host machine has a linked library or not? Should I not look inside the container rather?

That being said, I am running NixOS on the host. Linked libraries might not be where you'd expect them to be. I am running docker containers here so that I have an independent environment from my host machine.

Edit: Turns out the hint was correct, if installing apt install libelf-dev INSIDE THE CONTAINER that solves the issue.

That however is a bug in the image on dockerhub.

<!-- gh-comment-id:2425157998 --> @ic4-y commented on GitHub (Oct 20, 2024): I am running this in docker. Maybe I am missing something, but why would it matter if my host machine has a linked library or not? Should I not look inside the container rather? That being said, I am running NixOS on the host. Linked libraries might not be where you'd expect them to be. I am running docker containers here so that I have an independent environment from my host machine. Edit: Turns out the hint was correct, if installing `apt install libelf-dev` INSIDE THE CONTAINER that solves the issue. That however is a bug in the image on dockerhub.
GiteaMirror commented 2026-04-12 15:32:17 -05:00
Author
Owner
Copy Link

@skobkin commented on GitHub (Oct 22, 2024):

Looks like my #7320 is probably a duplicate of this.

So, just waiting for fixed image then?

<!-- gh-comment-id:2429774717 --> @skobkin commented on GitHub (Oct 22, 2024): Looks like my #7320 is probably a duplicate of this. So, just waiting for fixed image then?
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 docker
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#4625
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?