The sgl-project organization has a notable public GitHub presence with a variety of repositories primarily focusing on Python, Go, and C++. Key projects include SGLang, a framework for large language models, and mini-sglang, which simplifies complex LLM serving systems. Their repositories serve as valuable resources in the field of machine learning and model serving.
Top languages
Public repositories
sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
mini-sglang
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
SpecForge
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
sgl-learning-materials
Materials for learning SGLang
sglang-omni
SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models
genai-bench
Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
sglang-jax
JAX backend for SGL
rbg
A workload for deploying LLM inference services on Kubernetes
sgl-kernel-npu
SGLang kernel library for NPU
sgl-project.github.io
This is the documentation repository for SGLang. It is auto-generated from https://github.com/sgl-project/sglang
DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
sgl-kernel-xpu
SGLang kernel library for Intel XPU
whl
SGLang Kernel Wheel Index
sgl-flash-attn
Fast and memory-efficient exact attention
sgl-whl
SGLang wheels for multiple platforms
sgl-cookbook
Cookbook of SGLang - Recipe
sgl-eval
No description provided for this repository.
sgl-docs
No description provided for this repository.
cuLA
No description provided for this repository.
fast-hadamard-transform
Fast Hadamard transform in CUDA, with a PyTorch interface
ci-data
No description provided for this repository.
sglang-ci-stats
No description provided for this repository.
rbg-api
No description provided for this repository.
sgl-test-files
The test files for SGLang.
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
ome-crd
No description provided for this repository.
Frequently asked questions
What does sgl-project build on GitHub?
sgl-project develops a range of repositories focused on model serving frameworks, including SGLang and mini-sglang. Their work facilitates the deployment and training of large language models and includes tools for speculative decoding and benchmarking.
Which programming languages does sgl-project use?
sgl-project primarily uses Python, Go, and C++. Other languages used in their repositories include C++, Jupyter Notebook, and Cuda. This diverse set of languages supports their focus on machine learning and model serving technologies.
Are sgl-project's repositories public?
Yes, all of sgl-project's repositories are public on GitHub. This transparency allows users and developers to access their projects, contribute to their development, and utilize the resources provided for learning and implementation.
Is this exposure intended?
Monitor sgl-project with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account