Projects sharing features with DeepGEMM

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

FlashInfer is a library of high-performance GPU kernels purpose-built for accelerating large language model inference. It provides optimized implementations for attention operations (including flash attention, page attention, multi-head latent attention, and cascade attention) using paged key-value caches, fused kernel composition, and just-in-time compilation. The library also includes specialized kernels for mixture-of-experts layers, block-scaled low-precision quantization (FP8, FP4), and distributed collective communication. What distinguishes FlashInfer is its fused all-reduce communicat

JAX is a hardware-accelerated array library and automatic differentiation system for numerical computing. It provides a framework compatible with NumPy that extends array operations with a just-in-time compiler to transform Python functions into optimized kernels for execution on GPU and TPU accelerators. The system differentiates itself through the use of an XLA-based compiler and a single program multiple data sharding model. These capabilities allow the library to distribute large-scale computations across multiple hardware accelerators using both automatic parallelization and manual shard

TileLang is a Python-embedded domain-specific language compiler that JIT-compiles and autotunes GPU kernels. It uses a tile-based DSL, automatic software pipelining, and parallel autotuning to generate optimized GPU kernels at runtime. It supports tensor core operations with Pythonic syntax, automatic memory management, and thread mapping. The compiler searches over tile sizes, thread counts, and scheduling policies, compiling and benchmarking candidates in parallel to find the fastest kernel. It also caches compiled binaries and tuning results to disk for reuse across sessions. TileLang inc

ArrayFire is a hardware-agnostic compute framework and JIT-compiled tensor engine designed for high-performance numerical computing. It serves as a GPU numerical computing library and parallel signal processing toolkit that abstracts hardware backends, allowing the same codebase to execute across various GPU architectures and CPUs. The project distinguishes itself through a JIT engine that uses expression compilation to fuse operations and minimize memory overhead. It employs a deferred execution graph to optimize computation chains and provides interoperability primitives to share data and e

oneDNN is a library for deep learning acceleration that provides optimized building blocks for neural network training and inference. It manages tensor computation across CPU and GPU hardware, enabling the execution of high-performance primitives for model training and neural network inference optimization. The project distinguishes itself through hardware-specific kernel optimization and the use of just-in-time compilation to target specific processor instruction sets. It supports quantized neural network execution using both static and dynamic quantization to reduce memory usage and increas

Ktransformers is a comprehensive framework designed for the operation, fine-tuning, and serving of large language models. It functions as a heterogeneous inference engine and quantized execution runtime, enabling the deployment of massive models by distributing computational workloads across both CPU and GPU resources. This architecture allows users to bypass local memory constraints, making it possible to run and train models that exceed the capacity of a single device. The project distinguishes itself through specialized support for sparse architectures, particularly mixture-of-experts mode

TensorRT-LLM is a platform and toolkit designed for compiling, optimizing, and serving transformer-based models on accelerated hardware. It functions as a framework that transforms machine learning models into efficient execution graphs, providing an engine to refine these models for specific hardware to maximize throughput and minimize latency during text generation. The project distinguishes itself through advanced execution strategies that manage the entire inference pipeline. It utilizes kernel-level fusion and static graph execution to optimize mathematical operations and computational f

FlashMLA is an LLM attention kernel library and inference acceleration library providing a collection of high-performance CUDA kernels. It implements multi-head latent attention mechanisms designed to reduce memory overhead and increase throughput during the forward and backward passes of large language model inference. The library utilizes quantized cache attention kernels to improve computation efficiency across both sparse and dense token processing. It specifically optimizes the prefill and decoding phases of model inference through these latent attention implementations. The project cov

Grok-1 is an open-weights large language model implementation featuring a sparse mixture-of-experts architecture. It is designed for high-performance text generation and natural language processing by activating only a subset of specialized expert layers per token. The model utilizes 8-bit weight quantization to reduce memory overhead and accelerate loading. To manage its high parameter count, the implementation supports activation sharding, which distributes the memory load across multiple hardware devices during execution. The project covers large-scale model inference, including text comp

LightLLM is a high-performance serving framework for deploying and executing large language models. It functions as a multi-GPU inference engine and server capable of handling dense architectures, mixture-of-experts designs, and multimodal models that process both text and images. The system is distinguished by its specialized support for Mixture-of-Experts models using expert parallelism and fused kernels. It implements structured text generation through deterministic state machines and pushdown automata to enforce precise output formats. To optimize throughput, the framework employs specula

Segment Anything Fast is a high-performance computer vision inference engine and image segmentation framework built for PyTorch. It provides a specialized environment for automated object isolation and mask generation, designed to process large-scale visual datasets with increased throughput. The project distinguishes itself through a suite of system-level optimization strategies that accelerate deep learning model performance. By utilizing graph-based model compilation, just-in-time kernel fusion, and hardware-aware quantization, it reduces computational latency and memory footprint. These t

cuda-python provides low-level Python bindings for the CUDA Driver and Runtime APIs. It serves as a programmatic wrapper for controlling device memory, managing hardware toolchains, and orchestrating execution graphs on NVIDIA GPUs, allowing for the compilation and launching of parallel kernels directly from Python. The project enables the development of SIMT kernels and the execution of mathematical algorithms on device memory. It integrates pre-compiled bytecode as custom operators and interfaces with accelerated device libraries to access low-level hardware functions without leaving the la

Genesis World is an embodied AI simulation platform designed for training robotic agents through physics-based interactions. It centers on a multi-physics simulation engine that integrates rigid body, particle, and finite element method dynamics, supported by a parallel simulation kernel compiler that translates Python functions into optimized GPU and CPU kernels. The platform features a photorealistic robot renderer that utilizes path-tracing and Gaussian Splatting to generate synthetic training data. It includes a domain randomization framework to vary lighting and physical parameters acros

Neon is a deep learning framework and hardware-abstraction machine learning stack used for designing, training, and deploying neural network architectures. It functions as a graph-based computation engine that utilizes just-in-time kernel compilation to optimize machine code for tensors. The platform decouples model definitions from execution kernels, allowing it to support multiple CPU and GPU backends. This architecture enables the distribution of computational workloads across parallelized hardware environments to increase processing speed and overall efficiency. The system covers the ful

Flux.jl is a deep learning framework and numerical computing toolkit written in Julia. It serves as a machine learning library for designing and training neural networks, providing a system for automatic differentiation to optimize model parameters. The framework enables deep learning development and machine learning research by representing layers as parameterized functions. It supports scientific machine learning, integrating neural networks into workflows for solving physical and mathematical problems. The toolkit provides native GPU acceleration for tensor computations and utilizes rever

This project is a CUDA programming course and technical guide focused on writing and optimizing GPU kernels for hardware acceleration. It provides structured learning resources for using the CUDA platform to execute operations on silicon architectures. The material covers the optimization of linear algebra kernels and the analysis of machine learning deployment. It includes guidance on identifying acceleration tools, mapping the deep learning ecosystem, and evaluating the frameworks used to move models from research to production environments. The scope extends to GPU performance optimizatio

ndarray is a multidimensional array library for Rust that serves as a linear algebra framework and scientific computing tool. It provides the core infrastructure for creating and manipulating n-dimensional arrays, functioning as both a parallel array processor and a toolkit for numerical data analysis. The library distinguishes itself by providing efficient slicing and memory views, allowing for data sharing without copying. It leverages optimized backend math libraries for high-speed matrix multiplication and distributes heavy mathematical iterations across multiple CPU threads to accelerate

Neural Compressor is a deep learning model compression toolkit and AI inference acceleration engine. It functions as an automated model quantization tool and hardware-aware model compiler designed to reduce the memory footprint of neural networks and decrease execution latency. The project provides specialized frameworks for optimizing large language models, utilizing weight-only quantization and hardware-specific kernels to improve the operational efficiency of generative AI workloads. It maps neural network operators to specialized CPU and GPU vector instructions to accelerate model executi

This project is a high-performance C++ and CUDA neural network library designed for fast training and inference of small networks on NVIDIA GPUs. It serves as a specialized backend for neural radiance fields and coordinate-based networks, providing a fused GPU kernel library and a hash grid encoder for transforming raw input dimensions into high-dimensional representations. The library distinguishes itself through the use of C++ template metaprogramming and fused-kernel execution, which merge neural network layers into single GPU device functions to eliminate memory bottlenecks. It leverages

LeetCUDA is a collection of high-performance GPU kernel libraries focusing on memory optimization, activation functions, and attention mechanisms. It serves as a reference library for CUDA kernel implementations, ranging from basic element-wise operations to complex neural network components, and provides Python bindings to integrate these kernels into deep learning workflows. The project is distinguished by its focus on low-level hardware optimizations. This includes the use of tensor cores for half-precision matrix multiplication, asynchronous data pipelining with double buffering, and shar

Tinygrad is a deep learning framework and tensor computation engine designed for building and training neural networks. It functions as a hardware abstraction layer that manages device memory, command queues, and kernel dispatching across heterogeneous computing architectures. By utilizing a lazy-evaluation approach, the framework constructs computational graphs that defer execution until data is explicitly required, allowing it to process only the necessary operations for a given result. The project distinguishes itself through a just-in-time compilation layer that transforms abstract comput

Triton is a parallel computing framework and high-level programming language designed for writing custom compute kernels. It functions as a deep learning compiler, translating complex mathematical operations into high-throughput instructions that maximize hardware utilization and memory efficiency on graphics processing units. The framework distinguishes itself through a hardware-agnostic compute abstraction that allows developers to define kernels without manual low-level tuning. It employs just-in-time compilation to generate optimized binary instructions at runtime, utilizing static data f

This project serves as a comprehensive educational resource and technical guide for mastering deep learning through the PyTorch framework. It provides structured tutorials and practical code examples designed to teach core machine learning principles, ranging from fundamental tensor operations to the construction of complex neural network architectures. The repository distinguishes itself by bridging the gap between theoretical concepts and hands-on implementation. It covers the development of generative applications, such as image synthesis and style transfer, while offering guidance on opti

This project is a deep learning library designed for training neural networks on irregular data structures, including graphs, 3D meshes, and point clouds. It functions as an extension to the PyTorch framework, providing specialized layers and kernels that enable the processing of complex, non-Euclidean information. The library distinguishes itself through a geometric deep learning toolkit that manages the unique requirements of graph-based data. It utilizes sparse matrix-based message passing to aggregate information across nodes and employs dynamic computational graph construction to accommo

This project is a comprehensive computer vision library for the PyTorch ecosystem, providing a standardized collection of neural network architectures, datasets, and high-performance transformation utilities. It serves as a foundational framework for building, training, and deploying deep learning models, offering a centralized model registry that allows developers to instantiate architectures with pre-trained weights for tasks such as image classification, object detection, and semantic segmentation. The library distinguishes itself through its modular approach to data and compute management