Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design
Deriving predictable scaling laws that govern the relationship between model performance and computational investment is crucial for designing and allocating resources in massive-scale recommendation systems. While such laws are established for large language models, they remain challenging for recommendation systems, especially those processing both user history and context features. We identify poor scaling efficiency as the main barrier to predictable power-law scaling, stemming from inefficient modules with low Model FLOPs Utilization (MFU) and suboptimal resource allocation. We introduce Kunlun, a scalable architecture that systematically improves model efficiency and resource allocation. Our low-level optimizations include Generalized Dot-Product Attention (GDPA), Hierarchical Seed Pooling (HSP), and Sliding Window Attention. Our high-level innovations feature Computation Skip (CompSkip) and Event-level Personalization. These advances increase MFU from 17% to 37% on NVIDIA B200 GPUs and double scaling efficiency over state-of-the-art methods. Kunlun is now deployed in major Meta Ads models, delivering significant production impact.
Code (0)
등록된 구현이 없습니다.
Tasks
Recommendation SystemsSimilar Papers 제목 키워드 기반
Establishing Task Scaling Laws via Compute-Efficient Model Ladders
We develop task scaling laws and model ladders to predict the individual task performance of pretrained language models (LMs) in the overtrained setting. Standard power laws for language modeling loss cannot accurately m…
Language ModelingLanguage ModellingMultiple-choiceCommunication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo
As we scale to more massive machine learning models, the frequent synchronization demands inherent in data-parallel approaches create significant slowdowns, posing a critical challenge to further scaling. Recent work dev…
Language ModelingLanguage ModellingLLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation
We present LLaTTE (LLM-Style Latent Transformers for Temporal Events), a scalable transformer architecture for production ads recommendation. Through systematic experiments, we demonstrate that sequence modeling in recom…
Recommendation SystemsWhy Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
Predictable behavior from scaling advanced AI systems is an extremely desirable property. Although a well-established literature exists on how pretraining performance scales, the literature on how particular downstream c…
Multiple-choiceQuestion AnsweringFast and Simplex: 2-Simplicial Attention in Triton
Recent work has shown that training loss scales as a power law with both model size and the number of tokens, and that achieving compute-optimal models requires scaling model size and token count together. However, these…
valid