xm:D's repositories
3DDFA
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
awesome-distributed-ml
A curated list of awesome projects and papers for distributed training or inference
bitsandbytes
8-bit CUDA functions for PyTorch
CLIP
Contrastive Language-Image Pretraining
ColossalAI
Colossal-AI: A Unified Deep Learning System for Big Model Era
course
高性能并行编程与优化 - 课件
CS-Notes
:books: Computer Science Learning Notes
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
denoising-diffusion-pytorch
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Hetu
A high-performance distributed deep learning system targeting large-scale and automated distributed training.
hfta
Boost hardware utilization for ML training workloads via Inter-model Horizontal Fusion
HUMUS-Net
HUMUS-Net: a Transformer-convolutional Hybrid Unrolled Multi-Scale Network architecture for accelerated MRI reconstruction
llm.c
LLM training in simple, raw C/CUDA
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
magvit2-pytorch
Implementation of MagViT2 Tokenizer in Pytorch
MiniGPT-4
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
mmdetection
OpenMMLab Detection Toolbox and Benchmark
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
monai
Implementations of recent research prototypes/demonstrations using MONAI.
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
rerope
Rectified Rotary Position Embeddings
taming-transformers
Taming Transformers for High-Resolution Image Synthesis
tmi
tmi!!!
V2rayU
V2rayU,基于v2ray核心的mac版客户端,用于科学上网,使用swift编写,支持vmess,shadowsocks,socks5等服务协议,支持订阅, 支持二维码,剪贴板导入,手动配置,二维码分享等
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
xiaomin-D
Config files for my GitHub profile.