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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Model][Doc] Add RTX PRO 6000 Blackwell support for DeepSeek-V4-Flash-Vision-Exp
- [Feat][BI][2/N] add batch-invariant DeepSeek V4 support (compressor)
- [KV Connector][Mooncake] Share one transfer planner between the protocol directions
- [Config] Hash MambaConfig in the compile cache identity
- [Bugfix][Prefix] Skip EAGLE block drop for KV-shared drafters + widen periodic SWA tail
- [CI] Fix mHC numerical test portability across GPU architectures
- [Bugfix][MRV2] Preserve MTP query lengths in idle DP batches
- [Frontend] Return Anthropic-format errors for request validation on /v1/messages
- [Kernel][XPU] Tensor-descriptor Q loads in Triton MLA decode attention
- [Bug]: Multimodal video loaders ignore --media-io-kwargs num_frames
- Docs
- Python not yet supported