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
- [RFC]: Separate Flashinfer GQA into TRTLLM and flashinfer backends.
- [Bugfix] Handle list slot_mapping in remaining KV-cache consumers
- [Bugfix][SM120][MLA] Enable DCP for FlashInfer sparse MLA decode
- [Bug]: Cutlass C3X `dispatch_scaled_mm` crashes on SM120 Blackwell (RTX PRO 6000) with FP8 block-scaled model (DeepSeek-V4-Flash)
- [Feature]: model runner v2 support prefill context parallelism & cp8+tp8=worldsize8
- [RFC]: Precise group-aware recovery for KV load failures on hybrid models
- [Bugfix] Add interlaced video deinterlacing via PyAV + yadif
- [Bugfix] Add per-type field validation to AnthropicContentBlock
- [Model] Support uneven TP3 Qwen3.5/Qwen3Next layouts
- [Bugfix][Scheduler] Skip lookahead allocation for running prefill chunks
- Docs
- Python not yet supported