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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: sleep level 2 causes gibberish outputs
- [CI Failure]: mi325_1: Transformers Nightly Models Test
- [FEAT][Performance]Optimize native sampling by removing expensive scatter
- docs: add guide to reduce PyTorch profiler overhead via env vars (#29564)
- [Bug]: v0.12.0 Dockerfile.cpu fails to build on ARM server
- [WIP][Feat][Sched] Add Peak Split & Tail Optimization Policies
- [Bug]: raise error when setting --pipeline_parallel_size > 3 in ray cluster
- [RFC] [QeRL]: Online Quantization and Model Reloading
- [Optimization]: Add fused router for GPTOSS
- [Frontend] Honor chat template for gpt-oss harmony (#23015)
- Docs
- Python not yet supported