This is usually due to sampling settings rather than model instability.

Parameters like temperature, top-k, and top-p introduce randomness. If these aren’t fixed, outputs will vary even for identical inputs. Set deterministic decoding for consistent responses, especially in production. Also verify that prompts don’t include dynamic metadata like timestamps.

Common mistakes:

1. Leaving temperature > 0 unintentionally

2. Mixing deterministic and sampled decoding

3. Assuming reproducibility by default

Determinism must be explicitly configured.