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
- [ROCm] Restore fast top_k_per_row kernels for sparse MLA when topk_tokens=2048
- [Frontend][Bugfix] Forward chat_template_kwargs through GPT-OSS Harmo…
- Revert "[Core] Replace routing replay with device cache and async D2H pipeline" (#39917)
- [Bugfix] Route INT8 GPTQ MoE to WNA16 fallback
- [Bugfix][gpt-oss] gate structured-output matcher on analysis close
- [CI] Narrow engine.yaml source dependencies
- [Bugfix] Fix authentication bypass on /inference/v1/generate
- [MoE] Move various experts classes to fused_moe/experts/
- [MM][Perf][CG] Enable encoder CUDA Graph for MiniCPM-V
- [WIP][Kernel] Fuse QK RMSNorm AR + RoPE for MiniMax M2
- Docs
- Python not yet supported