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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] MoE MBU: estimate distinct activated experts instead of perfect-load-balancing upper bound
- fix(security): handle prompt_embeds in XD-RoPE position init
- [KV Connector] Support piecewise prefix loading in MultiConnector
- [Tests][ROCm] Register DeepEP in the modular-kernel test sweep
- [Doc] Fix broken anchor links in fusions.md quick reference table
- [Bugfix] Don't crash engine on malformed output-socket frame (#44486)
- [ROCm][Kimi-K3] Fuse gated RMSNorm with per-token FP8 for KDA o_proj
- [Kimi-K3] Add FlashInfer speculative KDA backend
- [Bug]: Gemma4 parser drops tool calls when transitioning out of reasoning channel (<channel|>call:...)
- [Bug]: PP + async scheduling + spec decode: output_token_ids trim only runs on the last PP rank, desynchronizing the ranks until NCCL deadlocks
- Docs
- Python not yet supported