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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Move EAGLE drop from KV cache managers to coordinators
- [MTP][Runtime] Reuse draft attention metadata across draft steps
- [SM120][MLA] Fix FlashInfer MLA DCP/MTP decode path
- feat(gguf): add PRISM Q1_0 and Q1_0_G128 1-bit quantization support
- [Feature] silu block quant fusion Triton kernel
- Fix GLM tool results with auto chat template content format
- [Feature] Add dense MHA fallback for short-sequence NSA prefill
- [Feature] NIC binding support
- [Realtime][Video] Add streaming video input for real-time video understanding
- INT4 per-token-head KV cache + kv_dequant dispatch scaffold
- Docs
- Python not yet supported