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
- [Bugfix][Benchmark] Fix dataset stats plot filename
- [CPU][Zen] Route BF16 MoE inference through zentorch on AMD
- [Config] Add field validators for attention, KV/EC transfer, and KV events configs
- feat: support to OpenMOSS-Team
- [Kernel] Use FlashInfer CUDA BGMV MoE Kernel for Multi-LoRA MoE dispatch
- Kenn/rusty
- [Kernel] Fuse align and sort for small-batch many-expert routing
- [Bugfix] Add FlashInfer B12x to linear backend selection
- [Performance]: FlashInfer AR+RMSNorm fusion cap is ~2x too high on multimem NVLink Hopper (TP8): it displaces the faster multimem all-reduce in the 256KB-512KB band
- [Perf] Gate AR+RMSNorm fusion cap on the active fast all-reduce threshold
- Docs
- Python not yet supported