zhangjun

zhangjun.github.io

https://zhangjun.github.io

stable_diffusion_compile

compile stable diffusion to run faster

TensorRT-Server

TensorRT Server

WeChatMsg

提取微信聊天记录，将其导出成HTML、Word、CSV文档永久保存，对聊天记录进行分析生成年度聊天报告

Paddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Paddle-Lite

Multi-platform high performance deep learning inference engine (『飞桨』多平台高性能深度学习预测引擎）

BaiduPCS-Go

iikira/BaiduPCS-Go原版基础上集成了分享链接/秒传链接转存功能

community

PaddlePaddle Developer Community

FastChat

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

FasterTransformer

Transformer related optimization, including BERT, GPT

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

llm-tools

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLM

Megatron-LM

Ongoing research training transformer models at scale

my_notes

oneflow-diffusers

OneFlow backend for 🤗 Diffusers and ComfyUI

Paddle-Inference-Demo

PaddleFleetX

Paddle Distributed Training Examples. 飞桨分布式训练示例 Resnet Bert GPT MOE DataParallel ModelParallel PipelineParallel HybridParallel AutoParallel Zero Sharding Recompute GradientMerge Offload AMP DGC LocalSGD Wide&Deep

PaddleNLP

👑 Easy-to-use and powerful NLP library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis and 🖼 Diffusion AIGC system etc.

paper-reading

puck

stable-diffusion-webui-docker

stable diffusion webui docker

stable-fast

An ultra lightweight inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

StableTriton

The first open source triton inference engine for Stable Diffusion, specifically for sdxl

Taipy-Chatbot-Demo

A template to create any LLM Inference Web Apps using Python only

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.

torch-play

transformer_framework

framework for plug and play of various transformers (vision and nlp) with FSDP

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.

vllm

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