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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [XPU] Register KV offload mmap region as pinned host memory
- [RFC]: Report characters/second alongside tokens/second in vllm bench serve
- [XPU][Linear][MXFP4] enable torch asn mxfp4 linear backend on xpu
- [Perf][DSV4] Optimize global top-k index kernel with compile-time constants
- [XPU][Tests] Make packed-decode and merge_attn_states kernel tests device-agnostic
- [Security] Enforce server-side num_frames ceiling in VideoMediaIO merge
- [BugFix] Clamp indexer scheduler-metadata seq_lens to avoid OOB read in DeepGEMM paged-MQA metadata kernel
- [Bugfix] Fix mismatched logger format args and enable ruff PLE1205/PLE1206
- [CI][AMD][Disagg] Fix Kimi K2.5/K2.6 MXFP4 MLA backends on ROCm nightly for accuracy eval (disable aiter OPUS FMHA)
- [WIP][Feature] Add layerwise KV cache transfer support with mooncake session API
- Docs
- Python not yet supported