server: speed up cancel test setup

This commit is contained in:
ochafik 2024-09-29 21:04:27 +01:00
parent 0e9c4bf5af
commit d07387ca9c

View file

@ -12,7 +12,7 @@ Feature: Cancellation of llama.cpp server requests
# KV Cache corresponds to the total amount of tokens
# that can be stored across all independent sequences: #4130
# see --ctx-size and #5568
And 512 KV cache size
And 256 KV cache size
And 32 as batch size
And 2 slots
And 64 server max tokens to predict