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][Whisper] Native word-level timestamps (cross-attention + DTW)
- [Bugfix][OpenAI] Respect allowed_token_ids in beam search
- [Feature]: SSE keep-alive comments for idle periods
- [Frontend] Pass sampling params through Anthropic /v1/messages
- [Bugfix] Unify per-layer KV cache dtype selection across v1/v2 model runners
- [Bugfix][Core] Sync reused pinned input buffers under PP batch queue (fixes IMA with sparse MLA + PP)
- [KV Connector] Normalize list/tuple KV cache input in register_kv_caches
- [Bugfix] Coerce Python-repr None to JSON null for tool-call args
- [Attention] TRITON_MLA_SPARSE backend for SM80/SM121 sparse MLA (rebase & takeover of #38476)
- [RFC]: Design a shared warmup infrastructure for JITs
- Docs
- Python not yet supported