scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

ui - polish Avg Latency per Toke

Browse source
This commit is contained in:
Ishaan Jaff 2024-05-01 09:42:36 -07:00
parent e3ce97d33e
commit 0c2e9936ae
1 changed files with 3 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
ui/litellm-dashboard/src/components/model_dashboard.tsx
View file

@ -1108,6 +1108,8 @@ const handleEditSubmit = async (formValues: Record<string, any>) => {
<Grid numItems={2}> <Grid numItems={2}>
<Col> <Col>
<Card className="mr-2"> <Card className="mr-2">
<Title>Avg Latency per Token</Title><p className="text-gray-500 italic"> (seconds/token)</p>
<Text className="text-gray-500 italic mt-1 mb-1">average Latency for successfull requests divided by the total tokens</Text>
{ modelMetrics && modelMetricsCategories && ( { modelMetrics && modelMetricsCategories && (
<AreaChart <AreaChart
title="Model Latency" title="Model Latency"
@ -1122,22 +1124,7 @@ const handleEditSubmit = async (formValues: Record<string, any>) => {
)} )}
<Table>
<TableHead>
<TableRow>
<TableHeaderCell>Model</TableHeaderCell>
<TableHeaderCell>Median Latency/Token</TableHeaderCell>
</TableRow>
</TableHead>
<TableBody>
{modelLatencyMetrics.map((metric, idx) => (
<TableRow key={idx}>
<TableCell>{metric.model}</TableCell>
<TableCell>{metric.avg_latency_per_token.toFixed(4)}</TableCell>
</TableRow>
))}
</TableBody>
</Table>
</Card> </Card>
</Col> </Col>
<Col> <Col>