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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Step3p5ForCausalLM fails with pipeline parallelism
- [vLLM IR] 1/N Implement IR skeleton and rms_norm op
- Enable torch.compile for Aria model
- fix: use 'vllm_' instead of 'vllm:' as prefix for prom metrics name
- [Refactor] Replace `activation: str` with `MoEActivation` enum
- [LoRA] Add TMA support to quantized fused_moe_lora kernel
- [DRAFT] pd disagg config for kimi-k2-thinking or deepseek-r1
- [DevEnv][NixOS] Add NixOS development environment with CUDA support
- [CI Failure]: mi325_1: Entrypoints Integration Test (API Server 1)
- [wip] explore using layerwise reloading utils for fp8 online quant
- Docs
- Python not yet supported