Skip to content
Change the repository type filter

All

    Repositories list

    • sglang

      Public
      SGLang is a high-performance serving framework for large language models and multimodal models.
      Python
      Apache License 2.0
      6.9k30k6913.2kUpdated Jul 3, 2026Jul 3, 2026
    • JAX backend for SGL
      Python
      Apache License 2.0
      10929513871Updated Jul 3, 2026Jul 3, 2026
    • ci-data

      Public
      Python
      7101Updated Jul 3, 2026Jul 3, 2026
    • Python
      0000Updated Jul 3, 2026Jul 3, 2026
    • rbg

      Public
      A workload for deploying LLM inference services on Kubernetes
      Go
      Apache License 2.0
      672543916Updated Jul 3, 2026Jul 3, 2026
    • SGLang kernel library for Intel XPU
      Python
      MIT License
      3526127Updated Jul 3, 2026Jul 3, 2026
    • whl

      Public
      SGLang Kernel Wheel Index
      HTML
      MIT License
      112402Updated Jul 3, 2026Jul 3, 2026
    • SpecForge

      Public
      Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
      Python
      MIT License
      2779637165Updated Jul 3, 2026Jul 3, 2026
    • SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models
      Python
      Apache License 2.0
      235573111120Updated Jul 3, 2026Jul 3, 2026
    • sgl-docs

      Public
      MDX
      Apache License 2.0
      16601Updated Jul 3, 2026Jul 3, 2026
    • SGLang kernel library for NPU
      C++
      MIT License
      1491522971Updated Jul 2, 2026Jul 2, 2026
    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      MIT License
      1.1k2907Updated Jul 1, 2026Jul 1, 2026
    • sgl-eval

      Public
      Python
      Apache License 2.0
      5921Updated Jun 30, 2026Jun 30, 2026
    • Fast and memory-efficient exact attention
      Python
      BSD 3-Clause "New" or "Revised" License
      2.9k2202Updated Jun 26, 2026Jun 26, 2026
    • Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
      Python
      MIT License
      51308910Updated Jun 24, 2026Jun 24, 2026
    • FlashMLA

      Public
      FlashMLA: Efficient Multi-head Latent Attention Kernels
      C++
      MIT License
      1.1k001Updated Jun 24, 2026Jun 24, 2026
    • sgl-project.github.io

      Public archive
      This is the documentation repository for SGLang. It is auto-generated from https://github.com/sgl-project/sglang
      Jupyter Notebook
      38133132Updated Jun 16, 2026Jun 16, 2026
    • A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
      Python
      MIT License
      7204.5k1131Updated May 17, 2026May 17, 2026
    • rbg-api

      Public
      Go
      1000Updated May 8, 2026May 8, 2026
    • sgl-cookbook

      Public archive
      Cookbook of SGLang - Recipe
      JavaScript
      Apache License 2.0
      18628Updated May 5, 2026May 5, 2026
    • cuLA

      Public
      Python
      Apache License 2.0
      0200Updated Apr 8, 2026Apr 8, 2026
    • The test files for SGLang.
      MIT License
      3001Updated Feb 23, 2026Feb 23, 2026
    • ome-crd

      Public
      0000Updated Jan 15, 2026Jan 15, 2026
    • Materials for learning SGLang
      MIT License
      6484900Updated Jan 5, 2026Jan 5, 2026
    • Fast Hadamard transform in CUDA, with a PyTorch interface
      C
      BSD 3-Clause "New" or "Revised" License
      63200Updated Oct 15, 2025Oct 15, 2025
    • sgl-whl

      Public
      SGLang wheels for multiple platforms
      MIT License
      21110Updated Oct 13, 2025Oct 13, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.