autoawq

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

autogptq

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

awesome-developer-resource

이 레포지토리는 저의 관심사 그리고 유용한 개발 정보를 수록해놓았습니다.

computelibrary

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

convolutions-to-vision-transformers

[Not Official] Implementation of CvT, Convolutions to Vision Transformers

deep-complex-networks

[Not Official] Implementation Deep Comple Networks and Plug-in module (e.g. Neural Preprocessing Layer, ICLR 2018)

digging-into-self-supervised-monocular-depth-estimation

[Not Official] Implementation of monodepth2, ICCV 2019

generative-adversarial-network-tutorial

Implementation GAN for MNIST, Simpson, Pokemon

llama.cpp

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

llm-finetuning-tutorial

This repository is LLM finetuning tutorial using Gemma-2B

llm-korean-cci-2024

2024 국립국어원 참가 대회 (7.14 ~ 8.31)

mlx

MLX: An array framework for Apple silicon

nerf-representing-scenes-as-neural-radiance-fields-for-view-synthesis

[Not Official] Simple NeRF training pipeline, ECCV 2020

neural-network-pruning-tutorial

Tutorial impelmentation of Neural Network Pruning for VGG

phase-aware-deep-complex-unet

[Not Official] Implementation DC-UNet, ICLR 2019

pseudolab-nnlabmlai

nnLabmlai 한글화 작업

russellgeum

russellgeum.github.io

self-supervised-monocular-sceneflow-estimation

[Not Official] Implementation of monocular sceneflow estimation, CVPR 2020

speech-preprocessing

Speech Data Preprocessing Tool for Deep Learning

stand-alone-self-attention

[Not Official] Implementation of Stand-Alone-Self-Attention, NeurIPS 2019

temporal-convolution-resnet

[Not Official] Implementation of TC-Resnet, INTERSPEECH 2019

tensorrt-llm

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

tvm

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

videodataset

비디오 데이터셋 핸들링 및 튜토리얼

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs