Verified75% confidenceFactExact time
The non-determinism of large language models stems from their autoregressive sampling process; even with temperature set to 0, differences in inference frameworks, batch sizes, and hardware floating-point operations can all cause output drift.
5
Sources
75%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
Related Claims
VerifiedEven when the temperature is set to 0, some inference frameworks still have non-determinism in underlying floating-point computations, causing output differences across hardware and across batches.85% similarUnverified由于模型工具选择受上下文窗口内容、温度参数、推理链路等因素影响，相同输入在不同运行中可能产生不同的调用序列，这种非确定性是Mock难以覆盖的根本原因78% similarUnverifiedEven with temperature set to 0 (greedy decoding), the behavior of large language models is still influenced by factors such as context length and positional bias in the attention mechanism.78% similarUnverifiedTemperature=0（贪心采样）也不能保证模型输出的确定性，至少有三个原因：浮点运算非结合性、MoE路由不确定性、服务端配置漂移77% similarUnverifiedAgent behavior is non-deterministic; even using the same prompt and temperature=0 settings, the same model's outputs at different points in time may exhibit subtle differences, influenced by factors such as floating-point arithmetic precision, batching strategies, and model version updates.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/563158API
curl https://kongchang.com/api/v1/knowledge/claims/563158MCP
get_claim(id=563158)