Parallelism-Aligned Pruning and Round-Aware Context Reuse for On-Device Multimodal Agents
TL;DR
PARC is presented, which combines parallelism-aligned structured pruning with lifetime-aware KV-cache reorganization, which uses first-order Taylor importance and grouped-query-attention-aware selection to make attention dimensions divisible by the target core count while preserving the query-to-key/value ratio and head dimension.
Abstract
On-device multimodal agents are limited by two deployment mismatches: pretrained attention structures may not divide evenly across the compute cores of an edge accelerator, causing irregular partitions; and standard prefix caching keeps historical visual tokens in the persistent KV cache, whose capacity grows with the number of rounds. We present PARC, which combines parallelism-aligned structured pruning with lifetime-aware KV-cache reorganization. At the model level, it uses first-order Taylor importance and grouped-query-attention-aware selection to make attention dimensions divisible by the target core count while preserving the query-to-key/value ratio and head dimension. At runtime, it separates the system prompt, persistent text history, and transient visual observations by lifetime, updating text history during tool execution so that historical images leave the persistent cache and more interaction rounds fit a fixed budget. On 2,062 GUI actions, the incremental interface shows no accuracy regression, and task-aware recovery training restores 98.7% of the action-type accuracy gap and the coordinate hit rate to the original level. Under seven-core deployment, hardware-aligned pruning reduces vision-encoder latency by 11.4%, improves decoding throughput by 23.8%, and lowers per-heap high-water memory by 12.7%; a parameter-matched control confirms that the speedup stems mainly from core alignment rather than parameter reduction.
