Fix incorrect metric display for request latency in console output

[markurtz]

No description provided.

[Copilot]

Pull Request Overview

This PR updates the label for the request latency metric in the benchmark console output.

• Changes the metric label from "Req Latency (ms)" to "Req Latency (sec)".
• Updates the display tuple for the request latency metric.

Comments suppressed due to low confidence (1)

src/guidellm/benchmark/output.py:892

• Ensure that the underlying request latency value is also converted from milliseconds to seconds. If the value is still in milliseconds, either convert it or revert the label change.

"Req Latency (sec)": (5, 7),

[nm-red-hat-upstream-automation-bot]

📦 Build Artifacts Available
The build artifacts (.whl and .tar.gz) have been successfully generated and are available for download: https://github.com/neuralmagic/guidellm/actions/runs/14776890501/artifacts/3044683840.
They will be retained for up to 30 days.

[nm-red-hat-upstream-automation-bot]

📦 Build Artifacts Available
The build artifacts (.whl and .tar.gz) have been successfully generated and are available for download: https://github.com/neuralmagic/guidellm/actions/runs/14778713301/artifacts/3045309579.
They will be retained for up to 30 days.