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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [WideEP] Remove naive all2all. Use allgather_reducescatter instead
- [DNM] testing docker build cache regression
- [Tracking issue]: Integrate flashinfer optimizations (DeepSeek)
- [WIP] Decompose all gather so clone is exposed to graph
- Optimize --help performance: Avoid torch import during help display
- [NVIDIA][test] Tests for flashinfer TRTLLM BF16 MoE
- [Core] Begin refactor of structured output backend batching logic [1/n]
- [wip] fp8 online quant with blockwise scaling
- [WideEP] Deprecate pplx all2all backend
- [Core] Reduce median/average TTFT by up to ~37% with Inter-Prefill-Budget
- Docs
- Python not yet supported