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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Kernel] Fix int32/uint overflow in merge_attn_states and permute_cols
- [Attention][MLA] FlashMLA sparse: enable DCP on the fp8 mixed-batch path and MTP with full cudagraphs
- [Bugfix][Frontend] Constrain forced named tool choice with empty parameters to a JSON object
- [MyPy] Fix mypy errors in kimi model family (3/5 files)
- [Feature/Gap] DSA models (GLM-5.1 / DeepSeek-V3.2-family, use_sparse=True) cannot select any attention backend on SM121 (GB10 / DGX Spark)
- [Kernel] [vLLM IR] [Perf] Add support for mixed input/weight dtype to rms norm quant fusion ops
- [Feature][ModelOpt]: Support NVFP4_AWQ checkpoints with native NVFP4 linear kernels
- [KV Connector][NIXL][Mooncake] CP-scaled scheduler block accounting for PD disaggregation with aligned DCP/PCP
- [Feature]: IndexCache support for DeepSeek V4
- [Kernel][MoE] Support GELU_TANH in FlashInfer CUTLASS MoE backend
- Docs
- Python not yet supported