Skip to content

@sgl-project sgl-project

Change the repository type filter

All

    Repositories list

    19 repositories

    • sglang

      Public
      SGLang is a fast serving framework for large language models and vision language models.
      cudainferencepytorchtransformeropenaimoellamavlmkimiblackwell
      Python
      •
      Apache License 2.0
      •3.3k•20k•526•806•Updated Nov 4, 2025Nov 4, 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
      •21•88•8•0•Updated Nov 4, 2025Nov 4, 2025

    • SpecForge

      Public
      Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
      trainingeaglepytorchllmfsdpsglangeagle3
      Python
      •
      MIT License
      •103•454•44•13•Updated Nov 3, 2025Nov 3, 2025

    • sgl-flash-attn

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •2.1k•13•0•0•Updated Nov 3, 2025Nov 3, 2025

    • sglang-jax

      Public
      JAX backend for SGL
      Python
      •
      Apache License 2.0
      •24•109•26•10•Updated Nov 3, 2025Nov 3, 2025

    • sgl-kernel-npu

      Public
      SGLang kernel library for NPU
      C++
      •
      MIT License
      •44•65•6•14•Updated Nov 3, 2025Nov 3, 2025

    • ome

      Public
      OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)
      k8sllamaoracle-cloudmodel-servingmodel-as-a-servicemulti-node-kubernetesllmllm-inferencedeepseeksglang
      Go
      •
      MIT License
      •43•303•31•21•Updated Nov 3, 2025Nov 3, 2025

    • whl

      Public
      Kernel Library Wheel for SGLang
      cudacutlasssglangflashinfer
      HTML
      •
      MIT License
      •4•15•0•0•Updated Nov 2, 2025Nov 2, 2025

    • rbg

      Public
      A workload for deploying LLM inference services on Kubernetes
      k8sllmsglangpd-disagg
      Go
      •
      Apache License 2.0
      •24•94•10•5•Updated Nov 2, 2025Nov 2, 2025

    • sgl-kernel-xpu

      Public
      SGLang kernel library for Intel XPU
      Python
      •
      MIT License
      •11•11•0•11•Updated Oct 31, 2025Oct 31, 2025

    • sgl-cookbook

      Public
      Make SGLang go brrr
      k8somellmdeepseekqwen2sglangllama3llama3-1qwen2-5deepseek-v3
      Creative Commons Zero v1.0 Universal
      •8•40•1•2•Updated Oct 28, 2025Oct 28, 2025

    • sgl-learning-materials

      Public
      Materials for learning SGLang
      MIT License
      •49•629•0•0•Updated Oct 26, 2025Oct 26, 2025

    • genai-bench

      Public
      Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
      Python
      •
      MIT License
      •29•227•5•5•Updated Oct 24, 2025Oct 24, 2025

    • sgl-test-files

      Public
      The test files for SGLang.
      MIT License
      •2•1•0•1•Updated Oct 22, 2025Oct 22, 2025

    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      •
      MIT License
      •734•21•0•1•Updated Oct 22, 2025Oct 22, 2025

    • FlashMLA

      Public
      FlashMLA: Efficient Multi-head Latent Attention Kernels
      C++
      •
      MIT License
      •896•0•0•0•Updated Oct 20, 2025Oct 20, 2025

    • fast-hadamard-transform

      Public
      Fast Hadamard transform in CUDA, with a PyTorch interface
      C
      •
      BSD 3-Clause "New" or "Revised" License
      •47•0•0•0•Updated Oct 15, 2025Oct 15, 2025

    • sgl-whl

      Public
      SGLang wheels for multiple platforms
      MIT License
      •1•11•0•0•Updated Oct 13, 2025Oct 13, 2025

    • tensorrt-demo

      Public
      TensorRT LLM Benchmark Configuration
      Python
      •4•13•0•0•Updated Jul 26, 2024Jul 26, 2024