mirror of
https://github.com/katanemo/plano.git
synced 2026-07-14 16:22:12 +02:00
6fc32b0152
has full dashboard with total requests, time per output token, time to first token, total latency, output sequence length, and input sequence length.
23 lines
482 B
YAML
23 lines
482 B
YAML
global:
|
|
scrape_interval: 15s
|
|
scrape_timeout: 10s
|
|
evaluation_interval: 15s
|
|
alerting:
|
|
alertmanagers:
|
|
- static_configs:
|
|
- targets: []
|
|
scheme: http
|
|
timeout: 10s
|
|
api_version: v1
|
|
scrape_configs:
|
|
- job_name: envoy
|
|
honor_timestamps: true
|
|
scrape_interval: 15s
|
|
scrape_timeout: 10s
|
|
metrics_path: /stats
|
|
scheme: http
|
|
static_configs:
|
|
- targets:
|
|
- host.docker.internal:19901
|
|
params:
|
|
format: ["prometheus"]
|