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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][Perf] Avoid fp32 round-trip dequant in fp8 KV paged decode
- [ROCm] Enable AITER unified attention on RDNA4 (gfx1201)
- [BugFix] Anchor "Dynamo bytecode transform" OTEL span to wall-clock time
- Fix PP broadcast hangs when a GPU device error (e.g. device lost) occurs on a peer worker
- [Bug]: MiniMax‑M3 (MSA) + NixlConnector: connector forces HND KV layout while MSA is NHD‑native, permuting the head axis under P/D disaggregation
- fix(worker): improve DCP/PCP error messages with actionable guidance …
- add torchcomms backend for xpu support
- [Bugfix] Parse compact sentence-transformers pooling_mode (>=5.4.0)
- [Bugfix] MLA: use _kv_b_proj_w_dtype for chunked-prefill cast (fix AWQ/GPTQ crash)
- [Feature]: Add a 2-bit KV-cache quantisation backend from Together AI
- Docs
- Python not yet supported