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
- [Perf] Speed up Mamba chunk metadata computation by ~6x
- [Feature]: [Parity with AMD SGLang] MoRI UMBP Offloading support
- [Core][Spec Decode] Reference implementation: per-request effective proposal lengths (RFC #48202)
- [CPU] Add CPU-tuned autotune configs for FLA (GDN) Triton kernels
- [Bugfix] Fix pooling input buffer race across chunked prefill steps
- [Model][LoRA] Add tower/connector LoRA support for Ultravox
- [Core][hybrid attention] group-aware recovery for KV load failures on hybrid models
- V1 multiprocess engine: sporadic 0.7-2s frozen engine step once per generate batch (absent with VLLM_ENABLE_V1_MULTIPROCESSING=0)
- [KV Connector][Mooncake] Skip lookup for locally reused prefix
- Update LayerNorm and dtype handling in gemma4_unified
- Docs
- Python not yet supported