Parser States Already Know: Structure-Conditioned KV Persistence for Structured Generation

TL;DR - PASK uses parser-state information to preserve schema-critical KV-cache entries during structured LLM generation. On Qwen3-4B, it improves function-calling accuracy under compression while reducing memory use and accelerating serving.

• Converts parser-derived structural signals into layer-group-specific KV persistence policies.
• Calibrates policies offline using task-error sensitivity and attention-output distortion, requiring only lightweight lookups online.
• At a 0.33 target KV budget, surpasses the strongest compressed baseline by an average of 17.39 percentage points across eight BFCL subcategories.
• Achieves up to 2.2× higher throughput, 3.3× lower time per output token, and 0.53× the peak GPU memory of full KV caching.