10 papers
ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation
Yuxin Chen, Liang Luo, Buyun Zhang +44
The paper introduces ROCS, a request-oriented compute sharing framework that restructures recommendation inference to evaluate shared request features once per request rather than…
LoKA: Low-precision Kernel Applications for Recommendation Models At Scale
Liang Luo, Yinbin Ma, Quanyu Zhu +21
Recent GPU generations deliver significantly higher FLOPs using lower-precision arithmetic, such as FP8. While successfully applied to large language models (LLMs), its adoption in…
UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs
Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Liang Luo +4
We introduce UnpredictaBench, an evaluation that tests the ability of large language models (LLMs) to capture true underlying distributions. As LLMs are increasingly used as substi…
Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design
Bojian Hou, Xiaolong Liu, Xiaoyi Liu +26
Deriving predictable scaling laws that govern the relationship between model performance and computational investment is crucial for designing and allocating resources in massive-s…
SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling
Zikun Liu, Liang Luo, Qianru Li +31
Recent advances in recommendation scaling laws have led to foundation models of unprecedented complexity. While these models offer superior performance, their computational demands…
LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation
Shali Jiang, Hua Zheng, Boyang Liu +40
Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from diminishing transfer ratio -- t…