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
- [CI] Enable sccache for Rust build under CUDA/ROCm
- [RFC]: [Roadmap] Mooncake Store Connector Feature Enrichment Roadmap
- Enable `MiniCPMV` for vLLM in CI
- [RFC]: Profiler support for CUDA graph capture tracing and roofline trace annotations
- [Feature]: Make vLLM compatible with Torch 2.12
- [Core] Update PyTorch to 2.12.1, torchvision to 0.27.1, triton to 3.7.1
- [Metrics] Add engine startup time gauge
- [Bugfix] Fix INC XPU MoE quantization routing for RoutedExperts
- [Bug]: In a dual-machine mixed setup running DP, some nodes fail to reach all_reduce on time, causing Gloo backend 'connection reset by peer'
- [RFC]: Image Token Pruning for Multimodal Models
- Docs
- Python not yet supported