Baidu Intelligent Cloud Tech Hub

Dec 17, 2025 · Artificial Intelligence

How AFD Splits Attention and FFN to Boost DeepSeek‑V3 Inference by Up to 19%

The article details the Attention‑FFN Disaggregation (AFD) technique used by Baidu Baige to separate self‑attention and feed‑forward network stages in DeepSeek‑V3 models, describing multi‑stage scheduling, three‑batch overlap, communication optimizations, and performance results that achieve up to 19% throughput improvement under a 100 ms SLO.