First-of-its-kind platform that combines multi-agent reinforcement learning with real-time market analysis to provide data-driven bidding recommendations that maximize both win probability and prof…

Efficient Triton Kernels for LLM Training

Examples for Recommenders - easy to train and deploy on accelerated infrastructure.

Meridian is an MMM framework that enables advertisers to set up and run their own in-house models.

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

Netease Youdao's open-source embedding and reranker models for RAG products.

Gigantic Graph Learning (GiGL) Framework: Large-scale training and inference for Graph Neural Networks

Easier audio-based machine learning with TensorFlow.

From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment

An easy-to-use framework for large scale recommendation algorithms.

python并发学习调研过程

A Go web framework for quickly building recommendation online services based on JSON configuration.

GLake: optimizing GPU memory management and IO transmission.

FeatInsight is a feature platform based on OpenMLDB

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

A modular graph-based Retrieval-Augmented Generation (RAG) system

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

Attribute (or cite) statements generated by LLMs back to in-context information.

Automatically create Faiss knn indices with the most optimal similarity search parameters.

Bridging LLM and Recommender System.