YongHuaZhang-BUAA

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

ADMM-NN

admm-pruning

Prune DNN using Alternating Direction Method of Multipliers (ADMM)

AI-Job-Notes

AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料）

algorithm

My LeetCode Solutions with Explanation and Time Complexity Analysis

Awesome-Pruning

A curated list of neural network pruning resources.

Interview-Notebook

:books: 技术面试需要掌握的基础知识整理

ml-road

Machine Learning Resources, Practice and Research

Model_Compression_Paper

Tools-NetworkModeViewer-Netron

Visualizer for neural network, deep learning and machine learning models

YongHuaZhang-BUAA/bitsandbytes

LLM：8-bit CUDA functions for PyTorch

YongHuaZhang-BUAA/cuda_hgemm

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

YongHuaZhang-BUAA/DeepSpeed

LLM：DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

YongHuaZhang-BUAA/ExplanationIntervention

LLM：PyTorch code for Can Language Models Teach? Teacher Explanations Improve Student Performance via Theory of Mind

YongHuaZhang-BUAA/FisherPruning

Finetuning：Group Fisher Pruning for Practical Network Compression(ICML2021)

YongHuaZhang-BUAA/FlanT5-CoT-Specialization

LLM：Implementation of ICML 23 Paper: Specializing Smaller Language Models towards Multi-Step Reasoning.

YongHuaZhang-BUAA/FlexGen

LLM：FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

YongHuaZhang-BUAA/FPGA-BDF

Avnet Board Definition Files

YongHuaZhang-BUAA/gptq

LLM：Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

YongHuaZhang-BUAA/hls4ml

Machine learning on FPGAs using HLS

YongHuaZhang-BUAA/hls4ml-tutorial

Tutorial notebooks for hls4ml

YongHuaZhang-BUAA/iree

👻

YongHuaZhang-BUAA/LaMini-LM

LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions

YongHuaZhang-BUAA/Lion

Lion: Adversarial Distillation of Closed-Source Large Language Model

YongHuaZhang-BUAA/llm-awq

LLM：AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

YongHuaZhang-BUAA/LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.

YongHuaZhang-BUAA/lm-evaluation-harness

LLM：A framework for few-shot evaluation of autoregressive language models.

YongHuaZhang-BUAA/LMOps

General technology for enabling AI capabilities w/ LLMs and MLLMs

YongHuaZhang-BUAA/neural-compressor

LLM：Provide unified APIs for SOTA model compression techniques, such as low precision (INT8/INT4/FP4/NF4) quantization, sparsity, pruning, and knowledge distillation on mainstream AI frameworks such as TensorFlow, PyTorch, and ONNX Runtime.

YongHuaZhang-BUAA/owq

LLM：Code for the "OWQ: Lessons learned from activation outliers for weight quantization in large language models".

YongHuaZhang-BUAA/pytorch-cifar

95.47% on CIFAR10 with PyTorch

YongHuaZhang-BUAA/qlora

LLM：QLoRA: Efficient Finetuning of Quantized LLMs

YongHuaZhang-BUAA/QuIP

Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"

YongHuaZhang-BUAA/RPTQ4LLM

LLM：Reorder-based post-training quantization for large language model

YongHuaZhang-BUAA/smoothquant

LLM：[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

YongHuaZhang-BUAA/Sparse-storage-formats

The codes of sparse storage formats for Vitis HLS

YongHuaZhang-BUAA/SpQR

LLM：SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

YongHuaZhang-BUAA/SqueezeLLM

LLM：SqueezeLLM: Dense-and-Sparse Quantization

YongHuaZhang-BUAA/wanda

LLM Pruning：A simple and effective LLM pruning approach.

YongHuaZhang-BUAA/XilinxBoardStore