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 supported44 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug][DeepSeek-V4][MTP] deep_gemm assertion: context_lens.is_contiguous() in paged MQA metadata
- [Bugfix] Improve DCP unsupported backend error message
- [Perf] fuse indexer topk and page table transform fusion for dpskv4
- feat: merge_attn_state fuses per-group fp8
- [Bug]: DeepSeek-V4-Flash hangs after ~6 requests with cudagraph_mode=FULL_AND_PIECEWISE + chunked prefill on SM 12.x (GB10)
- [Bugfix] Ensure DeepGEMM metadata gets contiguous context_lens
- [Bug]: can't run deepseek v4 flash
- [Misc] Allow install empty package from pip
- [MoE] Add FlashInfer CUTLASS FP8 ptpc MoE wiring
- [Bugfix] Validate post-reasoning structured output tokens in spec decode
- Docs
- Python not yet supported