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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [CPU][RISC-V] Auto-bind OMP threads and harden nobind path
- [MoE] Move triton experts to fused_moe/experts/
- [MoE] Move flashinfer cutlass moe to fused_moe/experts/
- [MoE] Move marlin moe to fused_moe/experts/
- [MoE] Move aiter experts to fused_moe/experts/
- [Models][Gemma3/Gemma4] Support hidden_act variants in gated MLP
- [Bug]: Regression in 0.19.1 - Gemma 4 26B MoE fails to load packed experts (KeyError: down_proj_packed). Worked in dev6.
- fix: correct typo 'Hyrbid' to 'Hybrid' in test-amd.yaml
- [Kimi] Track Kimi K2.5/K2.6 MLA + EAGLE serving on Blackwell (DCP4/DCP8, FP8 KV, draft backend split)
- [RFC]: Unified Device Capability Abstraction for Cross-Platform Feature Detection
- Docs
- Python not yet supported