fabfish

2022-applied-mathmetics-homework

计算机应用数学作业

Monarch-README

butterfly

Butterfly matrix multiplication in PyTorch

cramming

Cramming the training of a (BERT-type) language model into limited compute.

DALI-L3

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

flash-attention

Fast and memory-efficient exact attention

fly

personal research based on fly

gcn

Graph Convolutional Networks for Text Classification.

logging

MLPerf™ logging library

temp

triton

Development repository for the Triton language and compiler

ViTAE-Transformer

fish's fork of the official implementation for "ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias", "ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond".

BackRazor_Neurips22

[Neurips 2022] “ Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropogation”, Ziyu Jiang*, Xuxi Chen*, Xueqin Huang, Xianzhi Du, Denny Zhou, Zhangyang Wang

Bi-Mask

Pytorch implementation of our paper accepted by ICML 2023 -- "Bi-directional Masks for Efficient N:M Sparse Training"

Black-Box-Tuning

ICML'2022: Black-Box Tuning for Language-Model-as-a-Service & EMNLP'2022: BBTv2: Towards a Gradient-Free Future with Large Language Models

deit

Official DeiT repository

dynamic-sparse-flash-attention

eva

An Efficient Second-Order Algorithm with Sublinear Memory Cost

examples

Fast and flexible reference benchmarks

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

iTransformer

This is the official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting".

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

MeZO

MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

nlpfinal

nlpfinal for 2023

oneAPI_course

oneAPI - Data Parallel C++ course for students

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

pytorch_resnet_cifar10

Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.

RexLRScheduler

RexLRScheduler for timm

tipc

tipc-passes

LLVM passes for TIP programs