GPU/NPU — 3 Technical Articles

Jan 31, 2026 · Artificial Intelligence

How JD's 9N‑LLM Engine Powers Scalable Generative Recommendation at Massive Scale

This article details JD Retail's 9N‑LLM unified training framework that tackles the massive data, hardware heterogeneity, and algorithmic challenges of generative recommendation by integrating TensorFlow and PyTorch, supporting GPU/NPU, and delivering high‑throughput sample processing, sparse/dense optimization, and flexible reinforcement‑learning capabilities.

GPU/NPULarge-Scale AIRay

0 likes · 26 min read

How JD's 9N‑LLM Engine Powers Scalable Generative Recommendation at Massive Scale

JD Cloud Developers

Jan 30, 2026 · Artificial Intelligence

Scaling Generative Recommendation: Inside JD’s 9N-LLM Multi‑Framework Training Engine

This article details JD Retail’s 9N-LLM unified training engine, which integrates TensorFlow and PyTorch across GPU and NPU hardware to tackle the massive data, model size, and reinforcement‑learning complexities of generative recommendation, offering concrete components, performance benchmarks, and future directions.

GPU/NPUPyTorchTensorFlow

0 likes · 26 min read

Scaling Generative Recommendation: Inside JD’s 9N-LLM Multi‑Framework Training Engine

JD Retail Technology

Jan 30, 2026 · Artificial Intelligence

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

The article details JD Retail’s 9N‑LLM unified training engine—supporting TensorFlow and PyTorch, GPU and NPU, and both traditional and generative recommendation scenarios—explaining its architecture, high‑throughput sample engine, distributed sparse embedding system, five‑stage pipeline, UniAttention accelerator, and reinforcement‑learning capabilities that together enable TB‑scale data, B‑scale dense parameters, and efficient RL training for real‑world recommendation services.

Distributed TrainingGPU/NPUUniAttention

0 likes · 26 min read

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