Skip to content
@sgl-project

sgl-project

Pinned Loading

  1. sglang sglang Public

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Python 22.4k 4k

  2. sgl-learning-materials sgl-learning-materials Public

    Materials for learning SGLang

    716 54

  3. ome ome Public

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

    Go 356 54

  4. genai-bench 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 251 45

  5. SpecForge SpecForge Public

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

    Python 626 133

  6. sglang-jax sglang-jax Public

    JAX backend for SGL

    Python 218 61

Repositories

Showing 10 of 19 repositories
  • sglang Public

    SGLang is a high-performance serving framework for large language models and multimodal models.

    sgl-project/sglang’s past year of commit activity
    Python 22,431 Apache-2.0 4,044 645 (29 issues need help) 1,302 Updated Jan 14, 2026
  • SpecForge Public

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

    sgl-project/SpecForge’s past year of commit activity
    Python 626 MIT 133 52 (1 issue needs help) 22 Updated Jan 14, 2026
  • sglang-jax Public

    JAX backend for SGL

    sgl-project/sglang-jax’s past year of commit activity
    Python 218 Apache-2.0 61 79 (6 issues need help) 29 Updated Jan 14, 2026
  • sgl-project.github.io Public

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

    sgl-project/sgl-project.github.io’s past year of commit activity
    HTML 95 25 9 1 Updated Jan 14, 2026
  • genai-bench Public

    Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.

    sgl-project/genai-bench’s past year of commit activity
    Python 251 MIT 45 4 11 Updated Jan 14, 2026
  • sgl-flash-attn Public Forked from Dao-AILab/flash-attention

    Fast and memory-efficient exact attention

    sgl-project/sgl-flash-attn’s past year of commit activity
    Python 15 BSD-3-Clause 2,298 0 1 Updated Jan 14, 2026
  • sgl-kernel-npu Public

    SGLang kernel library for NPU

    sgl-project/sgl-kernel-npu’s past year of commit activity
    C++ 93 MIT 70 12 29 Updated Jan 14, 2026
  • whl Public

    Kernel Library Wheel for SGLang

    sgl-project/whl’s past year of commit activity
    HTML 17 MIT 5 1 0 Updated Jan 14, 2026
  • sgl-cookbook Public

    Cookbook of SGLang - Recipe

    sgl-project/sgl-cookbook’s past year of commit activity
    JavaScript 53 Apache-2.0 12 5 7 Updated Jan 14, 2026
  • ome Public

    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/ome’s past year of commit activity
    Go 356 Apache-2.0 54 32 (2 issues need help) 38 Updated Jan 14, 2026