Concept: Cache
Thoth: Uncovering Data-Dependent Memory Access Patterns via Annotation-Directed Load Sampling
Hardware prefetcher for irregular memory access in sparse data structures
PAT: Accelerating LLM Decoding via P refix- A ware A t tention with Resource Efficient Multi-Tile Kernel
Accelerating language model inference by reusing shared prompt cache across concurrent requests
Angular query orchestration reduced redundant GraphQL requests
Reducing redundant data fetching and improving load times in modular web applications
