SGLang is a fast serving framework for large language models and vision language models.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Better Harness Tools, not merely storing the archive of leaked Claude Code but also make shit things done. Now rewriting in Rust.

Collection of SLURM deployment scripts for various hardware + sglang disaggregation variants

FlashMLA: Efficient Multi-head Latent Attention Kernels

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…

A high-throughput and memory-efficient inference and serving engine for LLMs

CUDA Templates for Linear Algebra Subroutines

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Open deep learning compiler stack for cpu, gpu and specialized accelerators

A Tensor Algebra SuperOptimizer for Deep Learning

Prevents your Mac from going to sleep.

A common bricks library for building scalable and portable distributed machine learning.

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators

Open Neural Network Exchange

Caffe2 is a lightweight, modular, and scalable deep learning framework.

A repository for storing pre-trained Caffe2 models.

CPU INFOrmation library (x86/ARM, Linux/Mach/NaCl)