🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
multimodal-prod-6 Stopped
View inference service metrics, scaling, and configuration.
Status: Stopped Model: llama-3.1-70b Runtime: TorchServe Replicas: 2/5 RPS: 1321
Back to List
Service ID
is-1380
Name
multimodal-prod-6
Status
Stopped
Model
llama-3.1-70b
Runtime
TorchServe
Replicas
2/5
Requests/sec
1321
P50 Latency
455ms
P99 Latency
1442ms
GPU Type
H100-80G
Created
2026-02-03

Resource Metrics

CPU Usage Memory

Activity Timeline

Event 1: Resource was created 1h ago
Event 2: Resource was updated 2h ago
Event 3: Resource was accessed 3h ago
Event 4: Resource was scaled 4h ago
Event 5: Resource was restarted 5h ago