🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
multimodal-staging-8 Running
View inference service metrics, scaling, and configuration.
Status: Running Model: llama-3.1-70b Runtime: Triton Replicas: 4/3 RPS: 3835
Back to List
Service ID
is-8917
Name
multimodal-staging-8
Status
Running
Model
llama-3.1-70b
Runtime
Triton
Replicas
4/3
Requests/sec
3835
P50 Latency
169ms
P99 Latency
1110ms
GPU Type
A10-24G
Created
2026-04-07

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