sgl-project

SGLang is a fast serving framework for large language models and vision language models.

sgl-project

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

sgl-project

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

sgl-project

A workload for deploying LLM inference services on Kubernetes

sgl-project

Kernel Library Wheel for SGLang

sgl-project

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

sgl-project