From 86a7113bd54886b3a1639b0a14d4bf4dc6ea514e Mon Sep 17 00:00:00 2001
From: Aaron Teo <aaron.teo1@ibm.com>
Date: Wed, 18 Mar 2026 01:12:10 +0800
Subject: [PATCH] tests: enable kv_unified to prevent cuda oom error on rtx
 2060

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
---
 tests/test-backend-sampler.cpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tests/test-backend-sampler.cpp b/tests/test-backend-sampler.cpp
index d4cd62c71e72..58361ae80aea 100644
--- a/tests/test-backend-sampler.cpp
+++ b/tests/test-backend-sampler.cpp
@@ -89,6 +89,7 @@ struct test_context {
         cparams.n_batch = 512;
         cparams.samplers = configs.data();
         cparams.n_samplers = configs.size();
+        cparams.kv_unified = true;
 
         // If n_seq_max is not specified, calculate it from configs
         if (n_seq_max < 0) {