Similar Items: CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference
- DCatalyst: A Unified Accelerated Framework for Decentralized Optimization
- ProactivePIM: Accelerating Weight-Sharing Embedding Layer With PIM for Scalable Recommendation System
- BranchySplit: Runtime-Adaptable Partitioning and Early Exits for Accelerated Edge Inference
- Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation
- Graph-accelerated Markov Chain Monte Carlo using Approximate Samples
- Accelerating optimization over the space of probability measures