From de9d71125aa76ca689b9bea6e4f246240002dfde Mon Sep 17 00:00:00 2001
From: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com>
Date: Sat, 15 Jun 2024 13:38:16 -0400
Subject: [PATCH] add gptq_marlin test for bug report
 https://github.com/vllm-project/vllm/issues/5088 (#5145)

---
 tests/models/test_gptq_marlin.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tests/models/test_gptq_marlin.py b/tests/models/test_gptq_marlin.py
index e30100d9bf573..4abbc41c9c287 100644
--- a/tests/models/test_gptq_marlin.py
+++ b/tests/models/test_gptq_marlin.py
@@ -40,6 +40,9 @@
     ("TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ", "gptq-8bit-128g-actorder_True"),
     # 8-bit, act_order==True, group_size=32
     ("TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ", "gptq-8bit-32g-actorder_True"),
+
+    # 4-bit, act_order==True, group_size=128
+    ("TechxGenus/gemma-1.1-2b-it-GPTQ", "main")
 ]