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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix: avoid JSON constraints for native tool parsers
- [Quantization] Fix NVFP4 per-half global scale for fused gate_up_proj
- [Attention] Derive Triton 3D flash-decoding threshold from SM count a…
- [MRV2] Draw 64-bit uniforms for fp32 Gumbel sampling
- fix: return SSE content type from NIXL toy proxy
- [Kernel] Add opt-in cuda cache update for flash_attn_diffkv
- SWA Hybrid attention integrated with FlashInfer MLA + DCP
- DCP + split-q for speculative decoding support
- Fix MLA prefill cast for packed FP8 weight layouts
- [Bugfix] Verify functional P2P before enabling MiniMax fused allreduce+RMSNorm
- Docs
- Python not yet supported