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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: Cant use vllm on a multiGPU node
- [Feature]: Support outlines versions > v0.1.0
- [Feature]: KVPress
- Llama32 rocm FA support in upstream
- [Core] Free CPU pinned memory on environment cleanup
- Add support for reporting metrics in completion response headers in o…
- [V1] Replace traversal search with lookup table
- Update outlines support to v0.1.4
- [Bugfix] Fix some cases of `The client socket has timed out after 600s while trying to connect to`
- [Misc] Add multipstep chunked-prefill support for FlashInfer
- Docs
- Python not yet supported