SPARTA: A Sparse Ternary LLM Accelerator with Adaptive Attention and Unified Datapath for Long-Context Edge Inference.

arXiv:2610.34824v1 Announce Type: cross Abstract: LLMs on edge devices are constrained by limited memory and bandwidth. Although 1.58-bit ternary weights greatly reduce model storage, long-context inference is increasingly bottlenecked by KV-cache traffic and