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
- [Bugfix][Spec Decode] Clamp negative placeholder token ids before multimodal text embedding
- [RFC]: Compact candidate-set renormalization for native top-k/top-p sampling
- [Feature]: migrate NVSHMEM patches for RoCE from llm-d to vllm image
- [Bug]: No clamp-capable batched NVFP4 fused-MoE backend → DeepEP / wide-EP unusable for MiniMax-M3 NVFP4
- [Bugfix][Frontend] Accept Anthropic server tools without input_schema
- [Frontend] Add low-overhead /ready GPU health check
- [Bugfix][QWEN3-VL]: Align video handling with image handling and HuggingFace
- Revert "[Bugfix][Model] Support tensor parallelism for DiffusionGemma (#45719)" (#46177)
- [WideEP] Add NCCL EP all2all backend for expert parallelism
- [Bugfix] Parse JSON tool calls in Llama 4 pythonic parser
- Docs
- Python not yet supported