[https://nvbugs/5523315][fix] Fix serve benchmark test (#8255)

Signed-off-by: yechank <[email protected]>

Author: yechank-nvidia

tensorrt_llm/serve/scripts/benchmark_dataset.py

@@ -1133,7 +1133,7 @@ def sample(
             if len(prompts) >= num_requests:
                 break
             prompt = parser_fn(item)
-            mm_content = process_image(item["images"][0])
+            mm_content = [process_image(item["images"][0])]
             prompt_len = len(tokenizer(prompt).input_ids)
             if enable_multimodal_chat:
                 prompt = self.apply_multimodal_chat_transformation(

tests/integration/test_lists/waives.txt

@@ -284,7 +284,6 @@ accuracy/test_llm_api_pytorch.py::TestLlama3_2_3B::test_auto_dtype SKIP (https:/
 test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-image-False] SKIP (https://nvbugs/5444060)
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-video-False] SKIP (https://nvbugs/5444060)
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-video-True] SKIP (https://nvbugs/5444060)
-test_e2e.py::test_trtllm_multimodal_benchmark_serving SKIP (https://nvbugs/5523315)
 examples/test_llama.py::test_llm_llama_1gpu_fp8_kv_cache[llama-v2-7b-hf-bfloat16] SKIP (https://nvbugs/5527940)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput] SKIP (https://nvbugs/5481198)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale_chunked_prefill[latency] SKIP (https://nvbugs/5481198)