works on
entity-centric representation 1memory compression 1retrieval 1semantic memory 1streaming video understanding 1

From the 1 of 5 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs

Ahmed F. AbouElhamayed, Jordan Dotzel, Yash Akhauri +6

Large language models have high compute, latency, and memory requirements. While specialized accelerators such as GPUs and TPUs typically run these workloads, CPUs are more widely…