lm-sys / lm-sys/FastChat

argument 'tokens': 'NoneType' object cannot be converted to 'Sequence'

Open
#2,704 0 comments 0 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

When the qwen14b is running through the vllm, an error occurs: TypeError: argument 'tokens': 'NoneType' object cannot be converted to 'Sequence'.

CUDA_VISIBLE_DEVICES=1 python -m fastchat.serve.vllm_worker --model-path /share/LLMs/Qwen-14B-chat/ --tokenizer /share/LLMs/Qwen-14B-chat/ --model-names qwen-14b-vllm --host 0.0.0.0 --port 21008 --worker-address 'http://localhost:21008' --trust-remote-code --gpu-memory-utilization 0.4

What should I do?
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 by reproducing the reported failure with the fastchat.serve.vllm_worker command and the Qwen-14B model and tokenizer paths shown in the issue. Trace where the tokens value becomes None; done means the worker starts and serves the model without the reported TypeError.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.