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] Propagate fatal EngineCore shutdown
- [Feature]: FA2 is only supported on devices with compute capability >= 8
- [Core] Update PyTorch to 2.14.1, torchvision to 0.29.1, triton to 3.8.0 (release channel)
- [Bugfix] Remap ModelOpt q_scale to attn.q_scale
- [Attention] Skip stage2 for single-split Triton MLA decode
- [Bug]: Rust frontend renders caller-supplied chat templates with no evaluation budget: a 116-byte request body costs 55 CPU-seconds
- [Bugfix][Frontend] Import parser plugins under the vllm.* namespace so their logs survive
- [Bugfix] VLLM 0.27.0 has not been fixed MiniCPM-V-4.6 startup fails
- [Bugfix] Fix collect_env.py crash when pip list command fails
- [Bugfix][CPU] Workaround contradictory mamba validation after CPU MLA disables prefix caching
- Docs
- Python not yet supported