andreas/llama-swap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add prompt processing metrics (#250)

Browse Source 
- capture prompt processing metrics
- display prompt processing metrics on UI Activity page
This commit is contained in:
Benson Wong
2025-08-14 10:02:16 -07:00
committed by GitHub
parent a186318892
commit 74c69f39ef
4 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ui/src/contexts/APIProvider.tsx
View File

@@ -28,6 +28,7 @@ interface Metrics {
model: string;
input_tokens: number;
output_tokens: number;
prompt_per_second: number;
tokens_per_second: number;
duration_ms: number;
}

2
ui/src/pages/Activity.tsx
View File

@@ -51,6 +51,7 @@ const ActivityPage = () => {
<th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Model</th>
<th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Input Tokens</th>
<th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Output Tokens</th>
<th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Prompt Processing</th>
<th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Generation Speed</th>
<th className="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider">Duration</th>
</tr>
@@ -62,6 +63,7 @@ const ActivityPage = () => {
<td className="px-6 py-4 whitespace-nowrap text-sm">{metric.model}</td>
<td className="px-6 py-4 whitespace-nowrap text-sm">{metric.input_tokens.toLocaleString()}</td>
<td className="px-6 py-4 whitespace-nowrap text-sm">{metric.output_tokens.toLocaleString()}</td>
<td className="px-6 py-4 whitespace-nowrap text-sm">{formatSpeed(metric.prompt_per_second)}</td>
<td className="px-6 py-4 whitespace-nowrap text-sm">{formatSpeed(metric.tokens_per_second)}</td>
<td className="px-6 py-4 whitespace-nowrap text-sm">{formatDuration(metric.duration_ms)}</td>
</tr>