YuhuiXu

PC-DARTS. PC-DARTS:Partial Channel Connections for Memory-Efficient Differentiable Architecture Search

qa-lora. Official PyTorch implementation of QA-LoRA

BNET. Batch Normalization with Enhanced Linear Transformation

Trained-Rank-Pruning. Pytorch implementation of TRP

WLQ. caffe implementation of single level quantization

gptqlora. GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ

GPTQ-for-LLaMa. 4 bits quantization of LLaMA using GPTQ, zeros fp16

diracnets. Training Very Deep Neural Networks Without Skip-Connections

channel-pruning. Channel Pruning for Accelerating Very Deep Neural Networks

attention-transfer. Improving Convolutional Networks via Attention Transfer (ICLR 2017)

3D-Machine-Learning. A learning resource repository for 3D machine learning

KVCache-Factory. Unified KV Cache Compression Methods for Auto-Regressive Models

kvpress. LLM KV cache compression made easy

img_classification_pk_pytorch. Quickly comparing your image classification models with the state-of-the-art models (such as DenseNet, ResNet, ...)