yiliu30

neural-compressor

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

oneDNN

oneAPI Deep Neural Network Library (oneDNN)

pytorch-fork

Tensors and Dynamic neural networks in Python with strong GPU acceleration

torchao-fork

The torchao repository contains api's and workflows for quantization and pruning gpu models.

torchutils

Torch helper functions

yiliu30/DeepSpeed

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

yiliu30/neural-compressor

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

yiliu30/oneDNN

oneAPI Deep Neural Network Library (oneDNN)

yiliu30/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

yiliu30/torchao-fork

The torchao repository contains api's and workflows for quantization and pruning gpu models.

yiliu30/torchutils

Torch helper functions

yiliu30/accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

yiliu30/ai-pr-reviewer

AI-based Pull Request Summarizer and Reviewer with Chat Capabilities.

yiliu30/auto-awq-fork

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

yiliu30/auto-round

SOTA Weight-only Quantization Algorithm for LLMs

yiliu30/AutoGPTQ-fork

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

yiliu30/gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

yiliu30/gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

yiliu30/hqq-fork

Official implementation of Half-Quadratic Quantization (HQQ)

yiliu30/intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

yiliu30/ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, Axolotl, etc.

yiliu30/marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

yiliu30/ml-engineering

Machine Learning Engineering Open Book

yiliu30/nn-zero-to-hero

Neural Networks: Zero to Hero

yiliu30/notes

yiliu30/optimum-habana

Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)

yiliu30/subclass_zoo

yiliu30/tgi

Large Language Model Text Generation Inference

yiliu30/Torch-Fx-Graph-Visualizer

Visualizer for neural network, deep learning and machine learning models

yiliu30/training-operator

Training operators on Kubernetes.

yiliu30/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

yiliu30/tutorials

PyTorch tutorials.

yiliu30/xTuring

Easily build, customize and control your own LLMs

yiliu30/yi

yiliu30/yiliu30.github.io.tmp