monklof

bert

TensorFlow code and pre-trained models for BERT

faiss

A library for efficient similarity search and clustering of dense vectors.

linux-insides

A little bit about a linux kernel

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

MNN

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

cudf

cuDF - GPU DataFrame Library

cutlass

CUDA Templates for Linear Algebra Subroutines

mace

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

HIP

HIP: C++ Heterogeneous-Compute Interface for Portability

patchelf

A small utility to modify the dynamic linker and RPATH of ELF executables

jittor

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

TensorRT

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

asm

Learning assembly for Linux x86_64

tinyflow

Tutorial code on how to build your own Deep Learning System in 2k Lines

sequence_tagging

Named Entity Recognition (LSTM + CRF) - Tensorflow

how-to-optimize-gemm

TurboTransformers

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

maxas

Assembler for NVIDIA Maxwell architecture

runtime

A performant and modular runtime for TensorFlow

d2l-tvm

Dive into Deep Learning Compiler

CS143-Compilers-Stanford

My solutions to the programming assignments of the Stanford Compiler course.

gdev

First-Class GPU Resource Management: Device Drivers, Runtimes, and CUDA Compilers for Nouveau.

stack-machine

A simple stack-based virtual machine in C++ with a Forth like programming language

rnn_benchmarks

RNN benchmarks of pytorch, tensorflow and theano

python-cuda-profile