Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

A high-performance framework for training wide-and-deep recommender systems on heterogeneous cluster

Deep Pray(深度祈祷): LEGO for deep learning, Making AI easier, faster and cheaper👻

The source code for our paper "Scenario-Adaptive Feature Interaction for Click-Through Rate Prediction" (accepted by KDD2023 Applied Science Track), which proposes a model for Multi-Scenario/Multi-…

A simple and efficient Mamba implementation in pure PyTorch and MLX.

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).

Official PyTorch Implementation of "The Hidden Attention of Mamba Models"

An Attention Free Transformer without Self-Attention mechanism in PyTorch.

Implementation of a modular, high-performance, and simplistic mamba for high-speed applications

不使用Recbole实现Mamba4Rec

[RelKD'24] Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models

Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation

对推荐广告中，序列推荐、多任务推荐、跨域推荐、冷启动等方向主要算法学习笔记。

搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

Large Context Attention

Longformer: The Long-Document Transformer

Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch

[CAAI AIR'24] Minimize Quantization Output Error with Bias Compensation

PyTorch Implementation of CURL-Neural Network Pruning with Residual-Connections and Limited-Data

Codes for Layer-wise Optimal Brain Surgeon

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

PyTorch implementation of "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"

Papers for CNN, object detection, keypoint detection, semantic segmentation, medical image processing, SLAM, etc.

Base to channel pruned to ResNet18 model

Prune a model while finetuning or training.