From d07387ca9ceb3818db53e5e1fe897286a7952d80 Mon Sep 17 00:00:00 2001 From: ochafik Date: Sun, 29 Sep 2024 21:04:27 +0100 Subject: [PATCH] `server`: speed up cancel test setup --- examples/server/tests/features/cancel.feature | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/server/tests/features/cancel.feature b/examples/server/tests/features/cancel.feature index e7753b5dd..711236780 100644 --- a/examples/server/tests/features/cancel.feature +++ b/examples/server/tests/features/cancel.feature @@ -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