SparKV reduces time-to-first-token by 1.3x-5.1x and energy use by 1.5x-3.3x for on-device LLM inference by adaptively choosing between cloud KV streaming and local computation while overlapping execution and adjusting for runtime conditions.
Llm as a system service on mobile devices
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
DisCEdge manages LLM context in tokenized form replicated on edge nodes, delivering up to 14.46% faster median responses, 15% lower sync overhead, and 90% smaller client requests versus baselines while ensuring consistency.
ShadowNPU presents shadowAttn, a co-designed sparse attention system that uses NPU pilot compute and techniques like graph bucketing and per-head sparsity to minimize CPU/GPU fallback during on-device LLM inference while maintaining accuracy.
citing papers explorer
-
SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference
SparKV reduces time-to-first-token by 1.3x-5.1x and energy use by 1.5x-3.3x for on-device LLM inference by adaptively choosing between cloud KV streaming and local computation while overlapping execution and adjusting for runtime conditions.
-
DisCEdge: Distributed Context Management for Large Language Models at the Edge
DisCEdge manages LLM context in tokenized form replicated on edge nodes, delivering up to 14.46% faster median responses, 15% lower sync overhead, and 90% smaller client requests versus baselines while ensuring consistency.
-
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
ShadowNPU presents shadowAttn, a co-designed sparse attention system that uses NPU pilot compute and techniques like graph bucketing and per-head sparsity to minimize CPU/GPU fallback during on-device LLM inference while maintaining accuracy.