mistral-8x-7b stops generating in mid
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
I have noted that when using vllm worker sometimes mistral MOE model stops generating in middle. Is it happening for just me or anyone else. I am using the instruct version of mistral-8x-7b ie mistralai/Mixtral-8x7B-Instruct-v0.1.
I using below code to run the worker.
python3 -m fastchat.serve.vllm_worker --model-path mistralai/Mixtral-8x7B-Instruct-v0.1
prompt:
Give a code to show async await in python
The response:
Following parameters used for generation:
temperature = 0
max_tokens = 512
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the issue with fastchat.serve.vllm_worker, the mistralai/Mixtral-8x7B-Instruct-v0.1 model, the supplied prompt, temperature 0, and max_tokens 512. Compare runs that stop mid-response and capture the worker output; done means identifying a reproducible cause and confirming that generation completes reliably.
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