Originally posted by @tosokin on 2025-08-21 16:43 UTC
Category: General
Hello everyone,
Currently I am conducting performance testing on llamastack distribution and I tried to scrape some metrics from telemetry/metrics endpoint using this command:
curl -s http://llamastack-distribution-v2-23-service:8321/v1/telemetry/metrics/request_count -X POST -
H "Content-Type: application/json" -d '{"start_time": 1640995200}' | head -10
{"detail":"Not implemented: Querying metrics is not implemented"}
I was wondering if this feature will be implemented in the near future, these metrics could be very helpful.
Migrated from discussion #3225: https://github.com/llamastack/llama-stack/discussions/3225