sgl-project의 공개 GitHub 발자국

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

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

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

Materials for learning SGLang

SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models

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

JAX backend for SGL

A workload for deploying LLM inference services on Kubernetes

SGLang kernel library for NPU

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

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

SGLang kernel library for Intel XPU

SGLang Kernel Wheel Index

Fast and memory-efficient exact attention

SGLang wheels for multiple platforms

Cookbook of SGLang - Recipe

이 저장소에 대한 설명이 제공되지 않았습니다.

이 저장소에 대한 설명이 제공되지 않았습니다.

이 저장소에 대한 설명이 제공되지 않았습니다.

Fast Hadamard transform in CUDA, with a PyTorch interface

이 저장소에 대한 설명이 제공되지 않았습니다.

이 저장소에 대한 설명이 제공되지 않았습니다.

이 저장소에 대한 설명이 제공되지 않았습니다.

The test files for SGLang.

FlashMLA: Efficient Multi-head Latent Attention Kernels

이 저장소에 대한 설명이 제공되지 않았습니다.