luchangli03

export_llama_to_onnx

export llama to onnx

onnxsim_large_model

simplify >2GB large onnx model

BFGS-Optimization-for-curve-fitting

use BFGS optimization algorithm to solve problems like curve fitting

android_ndk_examples

android_ndk_examples

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)

cuda_sgemm

decoupleQ

A quantization algorithm for LLM

DeepLearningExamples

Deep Learning Examples

DejaVu

EAGLE

EAGLE: Lossless Acceleration of LLM Decoding by Feature Extrapolation

EasyNLP

EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

flash-attention-minimal

Flash Attention in ~100 lines of CUDA (forward pass only)

gemmlowp

Low-precision matrix multiplication

HashingDeepLearning

Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"

iris-estimator

kernel_tuner

Kernel Tuner

llm-awq

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

modelbox

为AI应用的开发者提供一套统一的高性能、易用的编程框架，快速基于AI全栈服务、开发跨端边云的AI行业应用。

models-1

A collection of pre-trained, state-of-the-art models in the ONNX format

MVision

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

OpenCL-examples-1

Simple OpenCL examples for exploiting GPU computing

pytorch-cifar

95.47% on CIFAR10 with PyTorch

speculative-decoding

Explorations into some recent techniques surrounding speculative decoding

tensorflow-1

An Open Source Machine Learning Framework for Everyone

torch2trt

An easy to use PyTorch to TensorRT converter

UGATIT-pytorch

Official PyTorch implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

weight_only_quant_rot

weight only quantization with rotation

xla

Enabling PyTorch on Google TPU

YHs_Sample

Yinghan's Code Sample