How Floating-Point Determinism Affects LLM Reproducibility
Running the same prompt through the same LLM does not always give the same output, even with temperature 0 and a fixed seed. One reason is floating-point arithmetic.…
Read articleTopic
Reproducibility
A result is easier to check when its inputs and settings are known. Versions and recorded conditions help explain differences between runs.
7 articlesAll blog posts
Articles
Can Provider Routing Change LLM Outputs?
Provider routing can change an LLM's output when a request reaches a different model version, fallback model, parameter configuration, precision level, inference engine, region, or runtime environment. Provider…
Read articleHow Model Updates Break LLM Reproducibility
A large language model (LLM) generates text, structured data, code, or tool calls from prompts. Hosted LLMs are not fixed functions of prompt text: providers can change models,…
Read articleHow to Test a Nondeterministic LLM Application
When an application calls an LLM, the same input can produce a different response on the next run. A test that compares the response with one expected string…
Read articleWhat Is Batch Invariance in LLM Inference?
Batch invariance means a request produces the same inference result when the server runs it alone, alongside other requests, at a different batch position, or under another supported…
Read articleHow Does Mixture-of-Experts Routing Affect LLM Repeatability?
If you send the same prompt to a mixture-of-experts (MoE) model several times at temperature 0, the answers can still differ. Routing is one possible reason. In each…
Read articleDoes Setting a Seed Make LLM Output Reproducible?
No. A seed can improve repeatability, but it does not guarantee identical large language model (LLM) output. It initializes the pseudorandom number generator used in token sampling; it…
Read article