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 supported46 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix engine crash when realtime streaming input is empty (#34532)
- feat(ep): add --expert-placement-file for custom MoE expert-to-rank mapping
- [Bug]: AllReduceFusionPass(config) takes 1s+ to construct
- [Bug]: BF16 NVFP4 Marlin produces garbled output on GPUs without native FP4 support
- Refactor oracle to separate support and selection
- Separate TRTLLM and Flashinfer backends
- [Core] Default to "mp" rather than "uni" distributed executor backend
- add tests from higher start point
- [Performance]: vLLM's throughput lags behind llama.cpp for single prompt
- [perf] silu early return for 0s
- Docs
- Python not yet supported