This page is for version 1.0.1.
For other versions, use one of these documentation indexes:
- 1.0.3 (default): https://docs.nvidia.com/nvcf/1.0.3/llms.txt
- 1.0.2: https://docs.nvidia.com/nvcf/1.0.2/llms.txt
- 1.0.1: https://docs.nvidia.com/nvcf/1.0.1/llms.txt
- Development: https://docs.nvidia.com/nvcf/dev/llms.txt
| Metric name | Metric type | Source | Description | Unit (where applicable) | Interesting Labels | Required Filters (where applicable) |
|---|---|---|---|---|---|---|
| axum_http_requests_total | Counter | nvcf-invocation-service:41337/metrics | Inovcation Service http requests count | status | exported_endpoint=~”^/v2/nvcf.*|^/health$”, namespace=“astro-tenant-nvcf-invocation-service” | |
| axum_http_requests_duration_seconds_count | Counter | nvcf-invocation-service:41337/metrics | Invocation Service http request counts | status | exported_endpoint=~”^/v2/nvcf.*|^/health$”, namespace=“astro-tenant-nvcf-invocation-service” | |
| axum_http_requests_duration_seconds_sum | Counter | nvcf-invocation-service:41337/metrics | Invocation Service durations of http requests | seconds | status | exported_endpoint=~”^/v2/nvcf.*|^/health$”, namespace=“astro-tenant-nvcf-invocation-service” |
| app_invocation_error | Counter | nvcf-invocation-service:41337/metrics | Invocation Service invocation errors | http_status_code | namespace=""astro-tenant-nvcf-invocation-service | |
| container_cpu_usage_seconds_total | Counter | nvcf-invocation-service:41337/metrics | Container cpu usage (used for uptime calculation) | container | container=“nvcf-invocation-service” | |
| container_memory_usage_bytes | Gauge | nvcf-invocation-service:41337/metrics | Container memory usage | bytes | container | container=“nvcf-invocation-service” |
| aws_requests_status | Gauge | AWS Cloud Watch | AWS request status | aws_status_code | namespace=“astro-tenant-nvcf-invocation-service”, service=“nvcf-invocation-service” | |
| nats_jetstream_publish | Counter | Pushed from Synadia | NATS Stream creation count | namespace | namespace=“astro-tenant-nvcf-invocation-service” |