Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing

LLMs edit text and code by autoregressively regenerating the full output, even when most tokens appear verbatim in the input. We study Copy-as-Decode, a decoding-layer mechanism that recasts edit generation as structured decoding over a two-primitive grammar: <copy lines=“i-j”/> references an input line range, <gen>…</gen> emits new content. A token-level FSM guarantees syntactic validity, and a serving-layer primitive updates the KV cache for each copy span via a single parallel-prefill forward rather than $N$ autoregressive steps – sharing the parallel-forward kernel of speculative decoding but with input tokens as the draft and program-enforced acceptance replacing probabilistic verification. We report an upper-bound analysis that requires no end-to-end training. (i) Kernel speedup: on Qwen2.5-{1.5B, 7B}, copying $N$ tokens via parallel prefill is $6.8\times$–$303\times$ faster than autoregressive ($N\in [8,512]$, A100 80GB bf16). (ii) Copy ceiling: on ProbeEdit and HumanEvalPack-Fix (Py/JS), $74$–$98\mathrm{\%}$ of gold tokens are reachable under the line-level primitive; composed with the empirical kernel over each corpus’s span histogram this yields a closed-form wall-clock bound of $29.0\times \mathrm{/}3.4\times \mathrm{/}4.2\times$ ($13.0\times$ pooled). A token-level extension reaches $91$–$99\mathrm{\%}$ coverage with $4.5\times$–$6.5\times$ floors. (iii) Pipeline losslessness: oracle programs round-trip through the deterministic resolver on all $482$ cases, localizing any downstream failure to span selection rather than the mechanism. A perturbation study shows pooled EM drops from $100\mathrm{\%}$ to $15.48\mathrm{\%}$ under off-by-one noise. A fine-tuning pilot on Qwen2.5-Coder-1.5B lifts HEvalFix-Py EM from $0\mathrm{/}33$ (untrained) to $12$–$17\mathrm{\%}$, a learnability signal, not a production selector. Batched-serving integration and multi-file coverage are scoped as follow-up.