library of algorithms to speed up neural network training

FlashInfer: Kernel Library for LLM Serving

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilizatio…

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A framework for few-shot evaluation of language models.

Computation using data flow graphs for scalable machine learning

PyTorch bindings for CUTLASS grouped GEMM.

Latency and Memory Analysis of Transformer Models for Training and Inference

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Repository for the Lux AI Challenge, season 2

Fast and flexible reference benchmarks

Frustum PointNets for 3D Object Detection from RGB-D Data

Appleseed Search Stack Docker composition. Uses Solr, Elasticsearch, MongoDB, Mono, DotNet, ASPNet, NGINX, MySQL, PostgreSQL

Development repository for the Triton language and compiler

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.

Fast and memory-efficient exact attention

📄 Test code blocks in your READMEs