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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KV Connector][NIXL][Mooncake] CP-scaled scheduler block accounting for PD disaggregation with aligned DCP/PCP
- Fix Responses Harmony instructions placement
- [Bugfix][Structured Outputs] Reject degenerate `structured_outputs` that crash EngineCore
- [Kernel] Fix strict-aliasing UB in scalar_type and minimax RMS kernel
- [Feature]: IndexCache support for DeepSeek V4
- [Bug]: vllm 0.22.1 metric monitor no display
- [Kernel][MoE] Support GELU_TANH in FlashInfer CUTLASS MoE backend
- [Core] Fix max_num_seqs async scheduling edge case
- [xpu][lora]: Align LoRA implementation with Punica GPU: fix _apply_expand rank mismatch, add_inputs hardcode, and MoE EP
- [Bug]: Integer overflow bug in concat_mla_q
- Docs
- Python not yet supported