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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: Qwen3.5 native MTP can be slower than no-MTP CUDA graph baseline despite good acceptance
- [Bugfix][Model] Harden DiffusionGemma self-conditioning matmul against torch.compile shape mismatch (#47129)
- [EC Transfer] Add MooncakeStoreECConnector for multimodal hidden-state transfer
- [Examples] Add Ray Data batch VLM inference example with ROCm support
- [ROCm]Migrating Deepseek V3.2 to vllm/models/deepseek_v32/
- [Doc] add AI Runway to integrations
- [Bugfix] Honor per-model DeepGEMM auto-disable in warmup and MoE selection (#47169)
- [Model] Add support for OpenPangu V2 model
- [Bugfix] Include SM12x in _is_fa4_supported() compute capability check
- [RFC]: Qwen3-ASR pseudo-streaming can repeat or miss segments
- Docs
- Python not yet supported