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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- WIP: [Mamba] Add separate CuTeDSL ReplaySSM checkpoints
- [Bugfix][Gemma4] Don't add empty thought block to past model turns in tool_chat_template_gemma4.jinja
- [ROCm][RDNA][MoE] Add hybrid W4A16 MoE backend for gfx115x (HIP decode + Triton prefill)
- [XPU][UT] Enable v1/attention tests on XPU
- [Test] Cover small-router unquantized linear batch invariance
- [Rust Frontend] Return routed experts on non-streaming chat and completions
- [Bug]: benchmark_moe.py fails with Ray 2.59 on ROCm: it replaces HIP_VISIBLE_DEVICES with ROCR_VISIBLE_DEVICES
- [Bugfix][NIXL] Fix NVFP4 KV corruption with different block sizes
- [Perf] Add encoder CUDA graph support for Cohere Transcribe
- [Bugfix][Core] Clear stale block-table row tails on shrinking add_row/move_row
- Docs
- Python not yet supported