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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core][Bugfix] Roll back eager prefix-cache registration on uncommitted free
- feat(attention): add fused RoPE and KV cache update for FlashAttention
- [Test][V1] Add unit tests for parallel sampling metrics
- [Feature]: Porting `MLAAttnQuantFusionPass` to manual fusion
- [Feature]: Porting `AllReduceFusionPass` to manual fusion
- [Feature]: Porting `ActivationQuantFusionPass` to manual fusion
- [Feature]: Porting `RopeKVCacheFusionPass` to manual fusion
- [Bug] CUTLASS MoE backend unavailable on SM_120/SM_121 (consumer Blackwell / DGX Spark) for tensor/token-scaled FP8 models
- [Bugfix] CohereModel.load_weights: skip modelopt _quantizer.* keys
- [Feature]: Porting `QKNormRoPEFusionPass` to manual fusion
- Docs
- Python not yet supported