AI RESEARCH
AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization
arXiv CS.LG
•
ArXi:2604.18137v1 Announce Type: cross Processing-in-Memory (PIM) architectures offer a promising solution to the memory bottlenecks in data-intensive machine learning, yet often overlook the growing challenge of activation memory footprint. Conventional PIM approaches struggle with massive KV cache sizes generated in long-context scenarios by Transformer-based models, frequently exceeding PIM's limited memory capacity, while techniques like sparse attention can conflict with PIM's need for data locality.