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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: On RDNA, hybrid-Mamba models fall back to Triton paged attention and decode collapses at long context
- [Performance][ROCm]: Fused bf16→fp32 router GEMM falls back to a standalone copy kernel on ROCm
- [Bugfix] Fix speculative decoding for short_conv (LFM2) models
- Fix Qwen Omni timing for presampled videos
- [Kernel] Fuse strided GDN RMSNorm gating on SM103
- [Bugfix][Spec Decode] Make EAGLE weight sharing TP-consistent
- docs: Add Apple Silicon/Metal execution requirements to quickstart
- [Bugfix] Skip generic required/named tool grammar for parsers that set supports_required_and_named
- [Frontend] Add stateless /v1/responses/render endpoint
- fix(security): enforce audio decode duration limit in NanoNemotronVL
- Docs
- Python not yet supported