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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][MoE] Fix MiniMax-M3.1 NVFP4 experts failing to load on Hopper
- [Bug]: NCCL weight sync: packed transfer fails to unpack misaligned tensors (pack_tensors has no alignment)
- [Bug]: Responses API 500s on assistant message with empty content list
- [Frontend][Responses] Reject empty assistant message content with 400 instead of 500
- [Bugfix][KVConnector] Fix Mooncake save offset stalls with evicted SWA blocks
- [Bugfix][Kernel] Synchronize Marlin MoE shared-buffer reuse
- [Feature]: Add pipeline parallelism support for Qwen3.8-Flash-Next (Qwen4Exp)
- [Bug]: `--attention-backend TORCH_SDPA` passes config validation, then dies with "Backend TORCH_SDPA must be registered before use" — a ViT-only tag offered as a valid option, whose `ValueError` bypasses the "Selected backend ... is not valid" path
- feat(compilation): add MoE FlashInfer fusion pass for kMoEFinalizeARResidualRMSNorm (#40544)
- [Bugfix][Frontend] Convert Responses content parts to chat parts
- Docs
- Python not yet supported