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
- [Kernel] Warm up flashinfer_cudnn BF16 GEMMs, not just flashinfer_cutedsl
- [ROCm][Kimi-K3] Run KDA speculative decode through AITER's fused kernel
- [Feature] Implement CuTe AllReduce fusion backend
- [Benchmark] Fix benchmark_block_fp8_gemm.py for current FP8 kernel API
- [Model][DCP] Support Qwen4Exp QSA
- [Core][HiSparse] Keep unpinned blocks last in the free queue
- [glm] [pcp] [1/n] wire pcp for hybrid GLM sparse MLA
- [glm] [pcp] [2/n] add KCP for hybrid GLM KDA
- [Bugfix][Attention] Skip the FlashMLA sparse bf16 prefill workspace on the fp8 mixed-batch path
- [Bugfix][NIXL] Stop clearing finished_sending for replicated-PCP producer ranks
- Docs
- Python not yet supported