docker / docker/model-runner

More apple metal woes

Open
#1,009 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Go
Stars
651
Forks
155
PR merge metrics
No merged PRs in 30d

Description

So I checked out other issues, this is a different issue altogether to any I can find so far

M1 Ultra 128GB RAM

> hey how are you doing?
Failed to generate a response: error response: status=500 body=unable to load runner: error waiting for runner to be ready: vllm-metal terminated unexpectedly: vllm-metal failed: r pid=3812)     super().__init__(
(APIServer pid=3812)   File "$HOME/.docker/model-runner/vllm-metal/lib/python3.12/site-packages/vllm/v1/engine/core_client.py", line 535, in __init__
(APIServer pid=3812)     with launch_core_engines(
(APIServer pid=3812)          ^^^^^^^^^^^^^^^^^^^^
(APIServer pid=3812)   File "$HOME/.docker/model-runner/vllm-metal/lib/python3.12/contextlib.py", line 144, in __exit__
(APIServer pid=3812)     next(self.gen)
(APIServer pid=3812)   File "$HOME/.docker/model-runner/vllm-metal/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 998, in launch_core_engines
(APIServer pid=3812)     wait_for_engine_startup(
(APIServer pid=3812)   File "$HOME/.docker/model-runner/vllm-metal/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1057, in wait_for_engine_startup
(APIServer pid=3812)     raise RuntimeError(
(APIServer pid=3812) RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}

I have replaced my home directory with $HOME; so you dont need to debug that.

Image Image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the vllm/v1/engine/core_client.py and vllm/v1/engine/utils.py entries in the reported traceback, then reproduce the runner startup failure on the listed M1 Ultra system. The missing root cause above the traceback must be identified before the runner can be considered fixed; verify that a model request completes successfully afterward.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, macos, python
Domain
ai, infrastructure
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.