[None][fix] AD test_trtllm_bench to use small model config and skip loading weights (NVIDIA#8149)

Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>

Author: MrGeva

tests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.py

@@ -452,6 +452,12 @@ def apply_rotary_pos_emb_ds(q, k, cos, sin, position_ids, unsqueeze_dim=1):
             "num_hidden_layers": 2,
         },
     },
+    "TinyLlama/TinyLlama-1.1B-Chat-v1.0": {
+        "llm_models_subdir": "llama-models-v2/TinyLlama-1.1B-Chat-v1.0",
+        "model_kwargs": {
+            "num_hidden_layers": 2,
+        },
+    },
 }