Tag

Sparse Training

0 views collected around this technical thread.

Alimama Tech
Alimama Tech
May 11, 2022 · Artificial Intelligence

PICASSO: An Industrial-Scale Sparse Training Engine for Wide-and-Deep Recommender Systems

PICASSO, Alibaba’s GPU‑centric sparse training engine for wide‑and‑deep recommender systems, merges identical embedding tables, interleaves data and kernel operations, and caches hot embeddings on GPU, eliminating the parameter server and delivering up to tenfold speedups over TensorFlow‑PS while maintaining model quality.

AlibabaGPU optimizationSparse Training
0 likes · 14 min read
PICASSO: An Industrial-Scale Sparse Training Engine for Wide-and-Deep Recommender Systems