From the 1 of 4 linked papers with an AI index.
4 papers
InferScale: GPU-Native KV Injection for Personalized LLM Serving
Peter Li, Prashant Pandey
The paper introduces InferScale, a GPU-native system that precomputes and caches key‑value (KV) representations of personalized memory facts for large language models, allowing dir…
How to Train Your Filter: Should You Learn, Stack or Adapt?
Diandre Miguel Sabale, Wolfgang Gatterbauer, Prashant Pandey
Filters are ubiquitous in computer science, enabling space-efficient approximate membership testing. Since Bloom filters were introduced in 1970, decades of work improved their spa…
KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs
Prashant Pandey
Whether attention key value (KV) states computed for one prompt for a small LLM can be reused to accelerate inference on a new similar prompt, giving an increase to the space to it…
Evaluating Learned Indexes for External-Memory Joins
Yuvaraj Chesetti, Prashant Pandey
Joins are among the most time-consuming and data-intensive operations in relational query processing. Much research effort has been applied to the optimization of join processing d…