server: tests: add infinite loop scenario

This commit is contained in:
Pierrick HYMBERT 2024-02-20 23:17:00 +01:00
parent 68574c6f98
commit b0b6d83c76

View file

@ -42,7 +42,7 @@ Feature: llama.cpp server
"""
Write another very long music lyrics.
"""
And 256 max tokens to predict
And 32 max tokens to predict
Given concurrent completion requests
Then the server is busy
And all slots are busy
@ -62,7 +62,7 @@ Feature: llama.cpp server
"""
Write another very long music lyrics.
"""
And 256 max tokens to predict
And 32 max tokens to predict
And streaming is enabled
Given concurrent OAI completions requests
Then the server is busy