From 76e868821a94072fbc87cb1fcca291694319eae8 Mon Sep 17 00:00:00 2001
From: Pierrick Hymbert <pierrick.hymbert@gmail.com>
Date: Fri, 8 Mar 2024 12:25:04 +0100
Subject: server: metrics: add llamacpp:prompt_seconds_total and
 llamacpp:tokens_predicted_seconds_total, reset bucket only on /metrics. Fix
 values cast to int. Add Process-Start-Time-Unix header. (#5937)

Closes #5850
---
 examples/server/tests/features/server.feature | 1 +
 1 file changed, 1 insertion(+)

(limited to 'examples/server/tests/features/server.feature')

diff --git a/examples/server/tests/features/server.feature b/examples/server/tests/features/server.feature
index f3b758c7..878ac136 100644
--- a/examples/server/tests/features/server.feature
+++ b/examples/server/tests/features/server.feature
@@ -29,6 +29,7 @@ Feature: llama.cpp server
     And   a completion request with no api error
     Then  <n_predicted> tokens are predicted matching <re_content>
     And   prometheus metrics are exposed
+    And   metric llamacpp:tokens_predicted is <n_predicted>
 
     Examples: Prompts
       | prompt                           | n_predict | re_content                       | n_predicted |
-- 
cgit v1.2.3