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
- [Bug]: Realtime STT (Voxtral realtime): self-sustained blank-token rut mutes live transcription for minutes over real speech
- [Bugfix][Spec Decode] Trim token_ids/logprobs left past a stop string under speculative decoding
- [Bug]: RuntimeError: scheduler_metadata must have shape (metadata_size) when using dspark speculative decoding with FP8 quantization on H20-3e
- [Bugfix][OpenAI] Respect allowed_token_ids in beam search
- Revert "[Bugfix][Gemma4] Fix FA4 mm_prefix mask: add sliding window and absolute q_idx" (#47332)
- [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
- [Bug]: collect_env.py crashes on Windows/macOS and pip-less uv environments
- [Bugfix] Fix collect_env.py crash on Windows/macOS and pip-less uv environments
- Docs
- Python not yet supported