Official PyTorch implementation of Agglomerative Token Clustering presented at ECCV 2024

An Open-source Platform for Inverse Lithography Technology Research

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference

Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''

10x Faster Long-Context LLM By Smart KV Cache Optimizations

CVPR2024 highlight.

Optical Neural Networks on PyTorch. diffractive propagation, nonlinear-photonic-activation

Supporting code for "End-to-end optical backpropagation for training neural networks".

Improving Generalist Model with Domain-Specific Experts

This repo contains ~4000 designs that are used to train GAN-OPC [DAC2018. TCAD2019]

This repo awesome-AI4EDA contains the source for the webpage: https://ai4eda.github.io, which is a curated paper list of awesome AI for EDA.

EUV Layer Hotspot Detection Benchmark Suit

This Repo Contains the Source Code and Pretrained Model for the Paper "Layout Hotspot Detection with Feature Tensor Generation and Deep Biased Learning", which is published in 54th Design Automatio…

(DAC2019 / TCAD2020) Faster Region-based Hotspot Detection.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

Extensible, parallel implementations of t-SNE

Transformers trained on Tiny ImageNet

[ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

⚡ A Fast, Extensible Progress Bar for Python and CLI

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch