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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Pin RMSNorm block size under batch-invariant mode
- [Model] Add Nemotron Ministral masked block-diffusion LM
- [Bugfix] Emit added/done lifecycle events for zero-delta streaming items
- Skip layerwise reload for non-quantized models
- TRITON_MLA_SPARSE fallback crashes on SM80 during CUDA graph capture
- feat: Internal session id for offloading
- [Core] Log result wait time in iteration details
- [Model] Add LongCat-2.0 (LongCat Sparse Attention + MTP)
- [Bugfix] Complete FlashInfer CUTLASS MXFP4 MoE wiring for DeepSeek-family models
- [Bugfix] Honor DeepSeek V4 checkpoints' MTP-layer compress_ratio entry (unscaled draft rope)
- Docs
- Python not yet supported