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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Add per request tracking of TTIT at RequestStateStats level
- [Bug]: sleep level 2 causes gibberish outputs
- [CI Failure]: mi325_1: Transformers Nightly Models Test
- [FEAT][Performance]Optimize native sampling by removing expensive scatter
- [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)
- [BugFix] Use late binding to avoid zmq port conflict race conditions
- [GPT OSS] Fix tool_choice required
- Docs
- Python not yet supported