Paran0idy

Paran0idy's Stars

• mindspore-ai/akg

  AKG (Auto Kernel Generator) is an optimizer for operators in Deep Learning Networks, which provides the ability to automatically fuse ops with specific patterns.

  Language:Python20938

• TiledTensor/TiledCUDA

  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.

  Language:C++1119

• HazyResearch/ThunderKittens

  Tile primitives for speedy kernels

  Language:Cuda1.5k57

• microsoft/BitBLAS

  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

  Language:Python33929

• FlagOpen/FlagGems

  FlagGems is an operator library for large language models implemented in Triton Language.

  Language:Python24221

• MarioLulab/Needle

  A basic deep learning library, comparable to a very minimal version of PyTorch.

  Language:Python101

• vllm-project/vllm

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

  Language:Python26.6k3.9k

• daattali/beautiful-jekyll

  ✨ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com

  Language:HTML5.3k16.1k

• isocpp/CppCoreGuidelines

  The C++ Core Guidelines are a set of tried-and-true guidelines, rules, and best practices about coding in C++

  Language:CSS42.5k5.4k

• cornell-zhang/allo

  Allo: A Programming Model for Composable Accelerator Design

  Language:Python12314

• Cambricon/triton-linalg

  Development repository for the Triton-Linalg conversion

  Language:C++13510

• cuda-mode/lectures

  Material for cuda-mode lectures

  Language:Jupyter Notebook2.4k244

• KnowingNothing/MatmulTutorial

  A Easy-to-understand TensorOp Matmul Tutorial

  Language:C++25727

• SForeKeeper/buddy-mlir

  An MLIR-Based Ideas Landing Project

  Language:C++21

• adam-maj/tiny-gpu

  A minimal GPU design in Verilog to learn how GPUs work from the ground up

  Language:SystemVerilog6.9k514

• chenzomi12/AISystem

  AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

  Language:Jupyter Notebook10.4k1.5k

• wuye9036/CppTemplateTutorial

  中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

  Language:C++9.5k1.6k

• buddy-compiler/buddy-mlir

  An MLIR-based compiler framework bridges DSLs (domain-specific languages) to DSAs (domain-specific architectures).

  Language:C++484159

• BobMcDear/attorch

  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

  Language:Python45121

• xtekky/gpt4free

  The official gpt4free repository | various collection of powerful language models

  Language:Python59.9k13.2k

• llvm/torch-mlir

  The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

  Language:C++1.3k475

• cuda-mode/resource-stream

  CUDA related news and material links

  1.1k67

• srush/Triton-Puzzles

  Puzzles for learning Triton

  Language:Jupyter Notebook96362

• unslothai/unsloth

  Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

  Language:Python15.5k1k

• Deep-Learning-Profiling-Tools/triton-viz

  Language:Python1226

• Jokeren/Awesome-GPU

  Awesome resources for GPUs

  46447

• gfvvz/Triton-Compiler

  Triton Compiler related materials.

  274

• sustcsonglin/flash-linear-attention

  Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

  Language:Python1.2k61

• ROCm/aotriton

  Ahead of Time (AOT) Triton Math Library

  Language:Python3213

• ModelTC/lightllm

  LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

  Language:Python2.3k190