Repositories list

• sglang

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

  cudainferencepytorch+ 17transformeropenaimoellamavlmkimiblackwell+ 10

  Python

  •

  Apache License 2.0

  •3.7k•21k•641•1k•Updated Dec 10, 2025Dec 10, 2025

• genai-bench

  Public

  sgl-project/genai-bench’s past year of commit activity
  Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.

  Python

  •

  MIT License

  •39•243•3•7•Updated Dec 10, 2025Dec 10, 2025

• ome

  Public
  OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)

  k8sllamaoracle-cloud+ 9model-servingmodel-as-a-servicemulti-node-kubernetesllmllm-inferencedeepseeksglang+ 2

  Go

  •

  MIT License

  •50•329•33•16•Updated Dec 10, 2025Dec 10, 2025

• sglang-jax

  Public
  JAX backend for SGL

  Python

  •

  Apache License 2.0

  •40•190•64•16•Updated Dec 10, 2025Dec 10, 2025

• SpecForge

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

  trainingeaglepytorch+ 4llmfsdpsglangeagle3

  Python

  •

  MIT License

  •115•536•47•16•Updated Dec 10, 2025Dec 10, 2025

• sgl-project.github.io

  Public
  This is the documentation repository for SGLang. It is auto-generated from https://github.com/sgl-project/sglang/tree/main/docs.

  HTML

  •24•92•8•1•Updated Dec 9, 2025Dec 9, 2025

• sgl-kernel-npu

  Public
  SGLang kernel library for NPU

  C++

  •

  MIT License

  •58•83•12•18•Updated Dec 9, 2025Dec 9, 2025

• sgl-kernel-xpu

  Public
  SGLang kernel library for Intel XPU

  Python

  •

  MIT License

  •13•15•0•13•Updated Dec 9, 2025Dec 9, 2025

• whl

  Public
  Kernel Library Wheel for SGLang

  cudacutlasssglang+ 1flashinfer

  HTML

  •

  MIT License

  •3•16•1•0•Updated Dec 8, 2025Dec 8, 2025

• rbg

  Public
  A workload for deploying LLM inference services on Kubernetes

  k8sllmsglang+ 1pd-disagg

  Go

  •

  Apache License 2.0

  •35•127•11•6•Updated Dec 3, 2025Dec 3, 2025

• sgl-learning-materials

  Public

  sgl-project/sgl-learning-materials’s past year of commit activity
  Materials for learning SGLang

  MIT License

  •49•679•0•0•Updated Dec 1, 2025Dec 1, 2025

• DeepGEMM

  Public
  DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

  Cuda

  •

  MIT License

  •771•21•0•1•Updated Nov 30, 2025Nov 30, 2025

• sgl-test-files

  Public
  The test files for SGLang.

  MIT License

  •2•1•0•1•Updated Nov 22, 2025Nov 22, 2025

• FlashMLA

  Public
  FlashMLA: Efficient Multi-head Latent Attention Kernels

  C++

  •

  MIT License

  •914•0•0•0•Updated Nov 20, 2025Nov 20, 2025

• sgl-flash-attn

  Public
  Fast and memory-efficient exact attention

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •2.2k•14•0•0•Updated Nov 18, 2025Nov 18, 2025

• fast-hadamard-transform

  Public
  Fast Hadamard transform in CUDA, with a PyTorch interface

  C

  •

  BSD 3-Clause "New" or "Revised" License

  •49•0•0•0•Updated Oct 15, 2025Oct 15, 2025

• sgl-whl

  Public
  SGLang wheels for multiple platforms

  MIT License

  •1•11•1•0•Updated Oct 13, 2025Oct 13, 2025