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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf] Batch the Whisper conv stem and CUDA-graph the fixed mel
- [Perf] Run Whisper log-mel on the GPU worker
- [Bugfix] Quantize Qwen3-Omni audio linears and drop the tower host sync
- [Bugfix] Drop the Ultravox encoder host sync and 3000-mel LoRA pad
- [Bugfix] Chunk conformer scores and keep FunASR adaptor frames
- [Perf][GDN] Add opt-in parallel inverse with fused zero stores
- [Feature][KV Connector][Mooncake] Add layerwise and chunk-wise KV transfer
- [Bugfix][Multimodal] Retain OpenCV streams until capture release
- [Spec Decode] Enable adaptive verification for `FlashInferMLASparseSM90Backend`
- [Attention][FlashInfer] Support DiffusionGemma mixed causal/bidirectional attention on TRTLLM-Gen
- Docs
- Python not yet supported