GEM训练：Meta如何将LLM级广告基础模型的效率提升一倍
GEM训练：Meta如何将LLM级广告基础模型的效率提升一倍
英文原标题: GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
Meta在Instagram和Facebook广告推荐的基础模型GEM现已在数千张最新GPU上以LLM规模训练，端到端训练效率翻倍至20-25% MFU，训练算力提升4倍。
Original Article
Meta’s Generative Ads Recommendation Model (GEM), the foundation model behind ads recommendations across Instagram and Facebook, now trains at LLM scale on several thousand of the latest-generation GPUs. This post goes into the details on how we achieved: doubling end-to-end (E2E) training efficiency to 20–25% Model FLOPs Utilization (MFU) while scaling training FLOPs 4x in […] Read More… The post GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model appeared first on Engineering at Meta.