JianchaoTan

PaintMixing

GPTs

leaked prompts of GPTs

ArtSpew

An infinite number of monkeys randomly throwing paint at a canvas

CodeFormer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

sd-webui-lcm

Latent Consistency Model for AUTOMATIC1111 Stable Diffusion WebUI

optuna

A hyperparameter optimization framework

ParaDance

Offers a toolset for comprehensive, multi-faceted large-scale data analysis and optimizations

ViT-Slim

Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”

spikingjelly

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers

LaVIT

LaVIT: Empower the Large Language Model to Understand and Generate Visual Content

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

DPM-OT

GNAS-MP

Pytorch Implementation of Rethinking Graph Neural Architecture Search from Message-passing (CVPR2021)

cords

Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.

L2_Compression

CogView

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

pdfdiff

Command-line tool to inspect the difference between (the text in) two PDF files

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

KwaiYii

pagmo2

A C++ platform to perform parallel computations of optimisation tasks (global and local) via the asynchronous generalized island model.

LOMO

LOMO: LOw-Memory Optimization

OptimalGradCheckpointing

SN-Net

[CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".

acceltran

[TCAD'23] AccelTran: A Sparsity-Aware Accelerator for Transformers

SqueezeLLM

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

retraining-free-pruning

[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers

jaxpruner

white-paper-for-large-model-security-and-privacy

The white paper which discusses the security and privacy problems of large models.

cutlass_fpA_intB_gemm

A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer