Running large language models on a single GPU for throughput-oriented scenarios.

Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.

A framework for few-shot evaluation of language models.

An implementation of a deep learning recommendation model (DLRM)

Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".

一些经典的CTR算法的复现; LR, FM, FFM, AFM, DeepFM, xDeepFM, PNN, DCN, DCNv2, DIFM, AutoInt, FiBiNet,AFN,ONN,DIN, DIEN ... （pytorch, tf2.0）

Python bindings for RocksDB

A library that provides an embeddable, persistent key-value store for fast storage.

LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.

JS runtime based on JerryScript

Platform for Internet of Things with JavaScript http://www.iotjs.net

The PebblesDB write-optimized key-value store (SOSP 17)

Revive unavailable songs for Netease Cloud Music

file文件上传的两种方式，点击按钮上传与拖放文件上传