[Bug]: Inconsistency with the field `min_duration_ms` in config.yaml

Bug Description

Issue

For small models and high concurrency numbers the following config snippet causes unexpected behavior:

settings:
  runtime:
    min_duration_ms: 600000
    max_duration_ms: 3600000

Expected

The number of samples is calculated dynamically to satisfy min_duration_ms.

Observed

The experiment is run to produce a performance and/or an accuracy reports, without any time check.
We have seen experiments with Duration: 74.34 seconds in their report.txt files.

Workaround

Explicitly set n_samples_to_issue chosen so, that the minimum time constrain is satisfied:

settings:
  runtime:
    min_duration_ms: 600000
    max_duration_ms: 3600000
    n_samples_to_issue: 100000

Steps to Reproduce

1. Create a config with big enough min_duration_ms, say, 10h, but without n_samples_to_issue.
2. Run an experiment with the config.
3. Check the time taken (or look into report.txt for the duration of the experiment).

Environment

inference-endpoints dad7d1a6462d91cd081cb58a07c51ed54fb0ba5e

Relevant Logs

Before submitting

• I searched existing issues and found no duplicates

Start by locating the runtime handling for min_duration_ms, max_duration_ms, and n_samples_to_issue in the configuration path. Reproduce the issue with a large minimum duration, then inspect report.txt and verify that experiments do not finish before the configured minimum duration when n_samples_to_issue is omitted.