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
- [Bug][ROCm][MoRIIO] In READ mode, a TP1 decode paired with a TP2 prefill shuts down on its first request (NotImplementedError) instead of refusing the unsupported pairing
- [Bug]: `--long-prefill-token-threshold` no longer protects short requests behind a long prefill since v0.31.0 (lone-request exemption, #57951)
- [Perf] Reduce multiprocess Prometheus logger CPU by 28% (3.64 s -> 2.62 s)
- [RFC]: Improving MooncakeConnector
- [Feature][Multimodal] Support KV-backed continuation through Generate inputs
- [WIP][Perf][CPU][DiffusionGemma] Optimize CPU runtimes
- [Bug]: GLM-5.3-Flash JIT-compiles DeepGEMM `tf32_hc_prenorm_gemm` during serving (20 mHC split-K variants are never warmed)
- [XPU] Compile passes porting llm-scaler decode optimizations, multi-row decode fixes (QKV/norm/GEMV/MoE router/all-reduce)
- [RFC]: TPSP Fusion Design
- [Docs] Add host kernel tuning guidance for engine-core polling and KV offload
- Docs
- Python not yet supported