add gptq_marlin test for bug report vllm-project#5088 (vllm-project#5145

)
xjpang · Jul 24, 2024 · de9d711 · de9d711
1 parent c1d82e0
commit de9d711
Showing 1 changed file with 3 additions and 0 deletions.
diff --git 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")
 ]