An on-device GPU inference framework reports 5-11x prefill speedups on mobile GPUs and up to 1.9x decode speedups versus open-source engines, but the order-of-magnitude claim does not hold on desktop or for decode.
LLM in a flash: Effi- cient Large Language Model Inference with Limited Mem- ory, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scaling On-Device GPU Inference for Large Generative Models
An on-device GPU inference framework reports 5-11x prefill speedups on mobile GPUs and up to 1.9x decode speedups versus open-source engines, but the order-of-magnitude claim does not hold on desktop or for decode.