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 supported34 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Re-sync parameter tp_rank after process_weights_after_loading (fix replicated / disable_tp weight reload)
- [Bugfix] Convert media fetch connection/DNS failures to HTTP 422
- [Bug]: GLM 5.2 forced toolcall left unparsed in content (glm 47 tool parser)
- fix(speech_to_text): use real per-chunk offsets for segment timestamps
- Fix/spec draft inherit model weights
- [KV Connector][Mooncake] Add tenant ID support to MooncakeStoreConnector
- [ROCm][CI] Avoid HIP init at config time via lazy aiter import in Quark OCP-MX
- Log fully resolved pooling config at startup
- [Frontend] Bound realtime STT audio_queue and per-session audio bytes
- [Bugfix] Fix parallel_tool_calls=null crash in Responses API from_request()
- Docs
- Python not yet supported