shayebuhui01 Goto Github PK

awesome-tensor-compilers

A list of awesome compiler projects and papers for tensor computation and deep learning.

bitsandbytes

8-bit CUDA functions for PyTorch

calculate-flops.pytorch

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

colossalai

Making large AI models cheaper, faster and more accessible

compiler-and-arch

A list of tutorials, paper, talks, and open-source projects for emerging compiler and architecture

conv2d_direct

cuassembler

An unofficial cuda assembler, for all generations of SASS, hopefully ：）

cuda-sgemm

博客地址：https://zhuanlan.zhihu.com/p/518857175

cuda-tensorcore-hgemm

博客地址：https://zhuanlan.zhihu.com/p/555339335

cuda-transpose

cuda_gemm

A simple high performance CUDA GEMM implementation.

cuda_hgemm

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction. 博客地址：https://zhuanlan.zhihu.com/p/639297098

cuda_sgemm

cutlass

CUDA Templates for Linear Algebra Subroutines

deep-learning-for-image-processing

deep learning for image processing including classification and object-detection etc.

deeplearningsystem

Deep Learning System core principles introduction.

flash-attention

Fast and memory-efficient exact attention

flash_attention_inference

Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

gpu-arch-microbenchmark

Dissecting NVIDIA GPU Architecture

how-to-learn-deep-learning-framework

how to learn PyTorch and OneFlow

how-to-optim-algorithm-in-cuda

how to optimize some algorithm in cuda.

how-to-optimize-gemm

how-to-optimize-gemm-tpoisonooo

row-major matmul optimization

how_to_optimize_in_gpu

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

labelme

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

matmultutorial

A Easy-to-understand TensorOp Matmul Tutorial. 博客地址：https://zhuanlan.zhihu.com/p/631227862

megatron-deepspeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

memory-efficient-convolution-for-deep-neural-network

npu-simulator

C++ Simulator for Neural Processing Unit