vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: input thread may die silently
- [Feature][V1][P/D]: Support P/D num_cached_tokens in response usage
- fix(benchmark): Prevent OOV error for small tokenizers in latency test
- [Bug]: RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s)
- [Bug]: After I updated vllm from 0.8.5 to 0.11.0, the generate speed has slowed down significantly
- [Bug] Pass correct ep_rank_start and ep_rank_end
- [Bug]: `set_model_tag` has strange interactions with global state
- [Bug]: `Prefix` not correctly propogated through Backend
- [Usage]: Does vLLM support a data-parallel group spanning multiple nodes when starting an online service?
- [Bug]: torch._dynamo hit recompile_limit using FlexAttention backend
- Docs
- Python not yet supported