How JD’s 9N‑LLM Engine Powers Scalable Generative Recommendation at Billion‑Scale

This article details JD Retail’s 9N‑LLM unified training engine, explaining the background of generative recommendation, the challenges of massive sparse and dense parameters, and the multi‑framework, multi‑hardware solutions—including efficient sample processing, large‑scale sparse embedding, dense scaling, UniAttention acceleration, and reinforcement‑learning integration—that enable industrial‑scale deployment.

AI InfrastructureGenerative RecommendationLarge-Scale Training

0 likes · 26 min read

How JD’s 9N‑LLM Engine Powers Scalable Generative Recommendation at Billion‑Scale

Alibaba Cloud Big Data AI Platform

Dec 17, 2024 · Artificial Intelligence

Build Chinese Vector Search with Alibaba Cloud AI and Elasticsearch Inference APIs

This guide walks you through creating sparse and dense vector inference endpoints on Elasticsearch using Alibaba Cloud AI services, demonstrates how to generate embeddings, perform completion, rerank results, and integrate RAG workflows for accurate Chinese‑language search.

AI searchCompletionDense Embedding

0 likes · 14 min read

Build Chinese Vector Search with Alibaba Cloud AI and Elasticsearch Inference APIs

Alibaba Cloud Developer

Dec 4, 2024 · Artificial Intelligence

How Alibaba’s GTE‑Multilingual Models Boost RAG with Long‑Doc and Multi‑Language Support

Alibaba's Tongyi Lab introduces the GTE‑Multilingual series, high‑performance encoder‑only models that support 8k‑token texts, 75 languages, elastic and sparse embeddings, and demonstrate superior retrieval‑augmented generation performance across multilingual and long‑document benchmarks.

AI model trainingSparse Embeddingelastic embedding

0 likes · 18 min read

How Alibaba’s GTE‑Multilingual Models Boost RAG with Long‑Doc and Multi‑Language Support

iQIYI Technical Product Team

Mar 1, 2024 · Artificial Intelligence

Advertising Data Characteristics and Sparse Large‑Model Practices at iQIYI

iQIYI’s ad ranking system replaces static, hash‑based embeddings with TFRA dynamic embeddings to efficiently handle massive sparse ID features, eliminates collisions and I/O bottlenecks, isolates memory during hot model swaps, enabling billion‑parameter models that boost revenue by 4.3 % while planning adaptive embedding sizes for future improvements.

AI recommendationAdvertisingSparse Embedding

0 likes · 10 min read

Advertising Data Characteristics and Sparse Large‑Model Practices at iQIYI