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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][NVFP4/FP8 MoE] Fix gated MoE crash on unaligned intermediate
- [Bug]: FlashInfer CUTLASS MoE selected on fp4-less builds (CUDA toolkit < 12.8); gpt-oss dies at engine start
- [Bug]: GLM 5.2 MTP didn't work in AMD MI300x
- [Bugfix][Spec Decode] Warm spec-sized logits all-gather during init
- [Bugfix][Kernel] Pass the correct expert count to WNA16 MoE block config
- [Bugfix][Frontend] Handle None/NaN/Inf logprob values when using FP8 quantization
- [Kernel] TRITON_MLA SWA
- [Feature]: [Batch-Invariant-Kernels] GDN_ATTN does not support batch-invariant mode for Qwen3.5/Qwen3.6 GDN models
- [Bugfix] Reject incompatible user-specified --block-size before model load
- [RFC]: Session-centric KV-cache orchestration over typed session identity
- Docs
- Python not yet supported