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.
Edgellm: Fast on-device llm inference with speculative decoding,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.