lm-sys / lm-sys/FastChat

Ascend NPU 910 running 行 fastchat.serve.model_worker an error is reported

Open
#2,903 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

python -m fastchat.serve.model_worker --model-path /home/ma-user/work/Qwen-7B-Chat --host 0.0.0.0 --device npu
When running the above code, an error is reported
2024-01-09 13:37:40 | INFO | model_worker | Register to controller
2024-01-09 13:37:40 | INFO | model_worker | Register to controller........................:503
2024-01-09 13:37:40 | ERROR | stderr | Traceback (most recent call last):
2024-01-09 13:37:40 | ERROR | stderr | File "/home/ma-user/anaconda3/envs/MindSpore/lib/python3.9/runpy.py", line 197, in _run_module_as_main
2024-01-09 13:37:40 | ERROR | stderr | return _run_code(code, main_globals, None,
2024-01-09 13:37:40 | ERROR | stderr | File "/home/ma-user/anaconda3/envs/MindSpore/lib/python3.9/runpy.py", line 87, in _run_code
2024-01-09 13:37:40 | ERROR | stderr | exec(code, run_globals)
2024-01-09 13:37:40 | ERROR | stderr | File "/home/ma-user/work/FastChat/fastchat/serve/model_worker.py", line 375, in
2024-01-09 13:37:40 | ERROR | stderr | args, worker = create_model_worker()
2024-01-09 13:37:40 | ERROR | stderr | File "/home/ma-user/work/FastChat/fastchat/serve/model_worker.py", line 346, in create_model_worker
2024-01-09 13:37:40 | ERROR | stderr | worker = ModelWorker(
2024-01-09 13:37:40 | ERROR | stderr | File "/home/ma-user/work/FastChat/fastchat/serve/model_worker.py", line 102, in __init__
2024-01-09 13:37:40 | ERROR | stderr | self.init_heart_beat()
2024-01-09 13:37:40 | ERROR | stderr | File "/home/ma-user/work/FastChat/fastchat/serve/base_model_worker.py", line 79, in init_heart_beat
2024-01-09 13:37:40 | ERROR | stderr | self.register_to_controller()
2024-01-09 13:37:40 | ERROR | stderr | File "/home/ma-user/work/FastChat/fastchat/serve/base_model_worker.py", line 98, in register_to_controller
2024-01-09 13:37:40 | ERROR | stderr | assert r.status_code == 200
2024-01-09 13:37:40 | ERROR | stderr | AssertionError
2024-01-09 13:37:43 | ERROR | stderr | /home/ma-user/anaconda3/envs/MindSpore/lib/python3.9/tempfile.py:821: ResourceWarning: Implicitly cleaning up
2024-01-09 13:37:43 | ERROR | stderr | _warnings.warn(warn_message, ResourceWarning)

Is it a root permission issue?

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

Reproduce the command with the Ascend NPU 910 setup, then start at fastchat/serve/model_worker.py:create_model_worker and ModelWorker initialization. Trace fastchat/serve/base_model_worker.py:register_to_controller and inspect the response behind the failed status-code assertion. Done means identifying whether permissions or another controller/setup condition causes the non-200 response and documenting the confirmed cause.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.