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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: PrefillDelayer for performant DPA
- [RFC]: [ROCm][DistInf]: Distributed Inference (Disaggregated P/D + Wide-EP) CI Enablement on ROCm
- [Bug]: Text PEFT LoRAs can silently no-op for wrapper models whose LM is mounted under language_model
- [Bug]: DeepSeek-V3/V3.1 tool parser drops the tool call when start+end tokens land in the same streaming delta
- docs: mention accelerated load formats for ModelOpt
- Fix/spec draft inherit model weights
- [Frontend] Bound realtime STT audio_queue and per-session audio bytes
- feat(spec_decode): Grammar-aware draft token sampling for structured outputs
- [Bug]: OffloadingConnector: DSpark draft-model KV-cache group's sparse storage causes external_prefix_cache_hits_total to be permanently 0
- Reject unsafe FlashInfer BF16-Q + spec decode + SWA on SM100
- Docs
- Python not yet supported