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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Compile] Add aot_eager backend for piecewise compilation
- [Feature]: Rust frontend profiler routes
- [RFC]: Heterogeneous TP<->DP parallelism across the P/D disaggregation boundary (MoRIIO)
- [Performance] Reduce update_from_output CPU overhead for decode batches
- [Core][KV-transfer] MoRIIO: flexible prefill-TP rank selection for heterogeneous TP<->DP reads
- fix: resolve vLLM performance and API issues
- [Performance]: Add a model-free microbenchmark for the frontend <-> EngineCore IPC path
- [Frontend] Add explicit video frame index selection
- [Model][DiffusionGemma] Bound sampler buffer memory under serving pressure
- [CPU] Fix segfault in mixed-batch GQA attention scheduling
- Docs
- Python not yet supported