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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Support per-parameter meshes in NCCL M2N weight transfer
- [Bugfix][Reasoning] Fix Kimi K3 response-only transitions
- [MRV2][Perf] Screened lm_head
- [Bugfix] Warm GLM DeepGEMM mHC pre-norm specializations
- [Bugfix][MoE] Reuse the FlashInfer CUTLASS MoE workspace across layers
- [feat] vllm framework for tpsp performance optimization
- [Bugfix][Core] Return False for retryable prefix-cache reset failures
- [Bugfix] Fix hf_overrides text_config on DeepseekV41Config
- [Perf][Model] Gemma 4: remove trailing image padding to enable FlashAttention in vision SDPA
- [Rust Frontend] Constrain MiniMax M3 tool calls with a nested argument grammar
- Docs
- Python not yet supported