Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference

2026-09-22

AI Summary

研究解决了大语言模型贪婪解码在不同精度下输出不一致的问题，通过选择性FP32 LM头部重计算方法提高了输出一致性。

Abstract

Greedy decoding from large language models is commonly treated as deterministic. We show it is not precision-invariant: the same model, prompt, and decoding algorithm produce different outputs in BF16 versus FP16 on identical hardware. Across our evaluations of six models (1.1B-7B parameters, four families; divergence additionally characterised at 12B) and three benchmarks, 49-100\% of prompts diverge; a single token flip often cascades into trajectory-level divergence. We develop an empirical error-propagation analysis and find that 22 layers of accumulated body error do not distinguish flipping from non-flipping steps; the outcome depends primarily on the top-two logit margin at the LM head relative to the directional perturbation between the top-two candidates. The analysis makes five testable predictions about intervention outcomes, including that applying more FP32 compute (broader scope) makes agreement worse. The experiments match all five predictions. The best-performing low-overhead intervention we evaluate, selective FP32 LM head recomputation, triggered only when the margin falls below a threshold, delivers +22-36 pp exact agreement on A10G (+12-21 pp on L4 and A100) at less than 4\% latency overhead in low-batch (batch size <=4) single-stream inference. We map the applicability boundary across six models and four batch sizes, and hypothesise that training-time precision stability is a determining factor. The method is a partial mitigation rather than a universal determinism guarantee: its benefit vanishes when body-originated error dominates, including at batch size >=8 and under end-to-end FP8 in our tests.

Problem

• greedy decoding
• precision-invariance
• output divergence
• large language models
• BF16 vs FP16

Innovation

• Greedy Decoding
• Precision Invariance
• Error Propagation Analysis
• Selective FP32 Recomputation
• Low-Overhead Intervention