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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Incremental MoE Expert Offloading — GPU Cache + Async Pipeline
- [Usage]: How to do offline inference on one rank in a distributed environment?
- [RFC]: Multi-tier KV offloading via the vLLM offloading connector
- [Feature]: PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
- [Startup][UX] Enable CUDAGraph memory profiling by default
- [Bug]: Gemma3n concurrent audio requests crash EngineCore — missing dynamic_dims on audio sequence dimension
- Energy Efficiency: 10 Mathematical Techniques for 60-70% AI Energy Reduction (Phi6Simple, FFT-Mix, Phi MoE)
- [CI] Swap to smaller models for MIG slice compatibility
- [Bugfix] Fix Gemma3n concurrent audio requests crashing EngineCore
- [Feature]: support affinity settings in helm chart
- Docs
- Python not yet supported