craft-zhang Goto Github PK

iree

👻

laser

The HPC toolbox: fused matrix multiplication, convolution, data-parallel strided tensor primitives, OpenMP facilities, SIMD, JIT Assembler, CPU detection, state-of-the-art vectorized BLAS for floats and integers

liveportrait

Make one portrait alive!

llama.cpp.bench

Port of Facebook's LLaMA model in C/C++

llm.c

LLM training in simple, raw C/CUDA

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

memperf

memory mountain on arm

micro-agent

An AI agent that writes (actually useful) code for you

ml-examples

Arm Machine Learning tutorials and examples

ml-quant

Research publication code for "Least Squares Binary Quantization of Neural Networks"

ml-ways

ML/DL Math and Method notes

mlas

modern-arm-assembly-language-programming

Source Code for 'Modern Arm Assembly Language Programming' by Daniel Kusswurm

nerf

Code release for NeRF (Neural Radiance Fields)

neural-networks-on-silicon

This is originally a collection of papers on neural network accelerators. Now it's more like my selection of research on deep learning and computer architecture.

nnieqat-pytorch

A nnie quantization aware training tool on pytorch.

nnpack

Acceleration package for neural networks on multi-core CPUs

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

openblas

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

opencl-training-code

Exercise and Solution code for OpenCL training (Intro and Advanced)

opencl-training-slides

PowerPoint Slides for the OpenCL training (includes Intro and Advanced)

openmp-tutorial

Exercises and Solutions for "Programming Your GPU with OpenMP: A Hands-On Introduction"

optimized-routines

Optimized implementations of various library functions for ARM architecture processors

optimizers

For optimization algorithm research and development.

ort-demo

onnx-runtime-demo

ppl.llm.kernel.cuda

ppl.llm.serving

ppl.nn

A primitive library for neural network

ppl.pmx

ppq

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.