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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core] Avoid repeated encoder-cache scans when freeing requests
- [Bug][KV Offload][P2P] Peer-down on one rank does not fail loads or block new loads to sibling ranks of the same source
- [Bugfix][Spec Decode] Synchronize adaptive DSpark decisions across TP ranks
- [ROCm][Perf] Add AITER paged MXFP4 indexing for DeepSeek V4 (gfx950)
- [Bug] DeepSeek-V4.1 on sm_120 (RTX PRO 2000 Blackwell): no FlashInfer SM120 sparse-MLA kernel for (num_heads=64, topk=1152); FlashMLA sparse is SM90a/SM100f only
- [Performance] Elide slow detokenizer delta suffix copy
- [Bugfix] Apply the mHC input RMSNorm in forward_native
- [Bugfix] Make hc_expand/hc_contract rank-agnostic
- [Bugfix][Kernel] Mask block-table loads in unified attention to prevent OOB read
- [Bugfix][Kernel] Fix UnboundLocalError in triton_scaled_mm when use_heuristic=False
- Docs
- Python not yet supported