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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Add --sleep-idle-ttl auto-sleep and wake-on-request
- [Rust Frontend] Beam search support for completions and chat completions
- [Feature] Gigachat 3.5 support
- [ROCm][Perf] Add Qwen3 AITER fused QKV/RoPE KV-cache path
- [Bug]: torch.xpu.device_count() returns 0 despite zeDriverGet() returning 1 — regression in XPU device detection
- [Bugfix] Add per-type field validation to AnthropicContentBlock
- [Feature][Whisper] Native word-level timestamps (cross-attention + DTW)
- [Bugfix][DeepSeek V4] Avoid SM100 FlashMLA cache shape mismatch
- [Bugfix][MoE] Handle older FlashInfer FP8 MoE signatures
- [Bug]: Realtime STT (Voxtral realtime): self-sustained blank-token rut mutes live transcription for minutes over real speech
- Docs
- Python not yet supported