Results for Token throughput based benchmarks

[farook-edev]

No description provided.

[github-actions]

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

[freedomtan]

LGTM.

[freedomtan]

• Should we add the unit for each numbers explicitly on the screen or we can leave them to tooltips when scores are clicked.
  • we are more adding the unit explicitly on the screen, let's think where to add the units. e.g., make "task name" clickable, and add the unit the i column. or make the text clickable.
• we should change the history screen, too

[farook-edev]

I've added the units next to the result values. As for the 🛈 icon, I was going to make multiple versions and see which one looked best, but then I noticed that the 'make the icon a clickable button and put the info there' idea has already been implemented and approved for the config screen as per #1028. So I opted to replicate the same UI in the result screen.

I also edited the history screen to have both QPS average for non token benchmarks and TPS average for token benchmarks. In addition to adding T/sec or Q/sec for each benchmark in the table below the summary.

[sonarqubecloud]

Quality Gate passed

Issues
40 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud

[freedomtan]

please add the time to first token to the "Result details"
let the time to first token time be the first enty.