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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- 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
- [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
- [Bug]: Gemma4 engine-based tool parser returns all bare-value arguments as strings (scilent behavior change)
- [Bug]: gigachat3, granite and granite-20b-fc tool parsers lose tool calls when the whole message arrives in a single streaming delta
- [ROCm]: Bump torch 2.12, torchvision, torchaudio, triton 3.7
- Docs
- Python not yet supported