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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] Make Whisper causal attention backend-agnostic
- [release 2.11] Update to torch 2.11
- [CI Failure]: LM Eval Large Models (H100x4) - Nemotron
- [ROCm] Default VLLM_ROCM_USE_AITER_FP4BMM=True crashes on MI300X (gfx942)
- [Bug]: [cpu] CPUFusedMOE passes MoEActivation enum to torch op expecting str
- [WIP][Bugfix] Fix xgrammar nanobind leaked objects at shutdown
- [Feature] Add VLLM_TRITON_AUTOTUNE with functional autotune control
- Bug: Speculative Decoding (MTP) Causes </think> Detection Failure in Structured Output + Reasoning Mode
- Refactor oracle to separate support and selection
- Separate TRTLLM and Flashinfer backends
- Docs
- Python not yet supported