update test list

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

Author: xinhe-nv

tests/integration/defs/accuracy/test_llm_api_pytorch.py

@@ -274,10 +274,11 @@ def test_ngram(self):
  @pytest.mark.parametrize("backend", ["xgrammar", "llguidance"])
  def test_guided_decoding(self, backend: str, mocker):
  mocker.patch.dict(os.environ, {"TRTLLM_XGUIDANCE_LENIENT": "1"})
- with LLM(self.MODEL_PATH,
- guided_decoding_backend=backend,
- disable_overlap_scheduler=True,
- cuda_graph_config=CudaGraphConfig()) as llm:
+ llm = LLM(self.MODEL_PATH,
+ guided_decoding_backend=backend,
+ disable_overlap_scheduler=True,
+ cuda_graph_config=CudaGraphConfig())
+ with llm:
  task = JsonModeEval(self.MODEL_NAME)
  task.evaluate(llm)
 

tests/integration/test_lists/qa/llm_sanity_test.txt

@@ -35,7 +35,7 @@ accuracy/test_llm_api_pytorch.py::TestLlama4MaverickInstruct::test_auto_dtype[tp
 accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_auto_dtype[tp8-cuda_graph=False]
 accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_auto_dtype[tp8ep4-cuda_graph=True]
 accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_auto_dtype[tp8ep8-cuda_graph=True]
-accuracy/test_llm_api_pytorch.py::TestMinistral8BInstruct::test_auto_dtype
+accuracy/test_llm_api_pytorch.py::TestMinistral8BInstruct::test_auto_dtype_gsm8k
 accuracy/test_llm_api_pytorch.py::TestMinistral8BInstruct::test_fp8
 accuracy/test_llm_api_pytorch.py::TestMinitron4BBaseInstruct::test_fp8_prequantized
 accuracy/test_llm_api_pytorch.py::TestMistral7B::test_auto_dtype
@@ -84,23 +84,16 @@ test_e2e.py::test_ptp_quickstart_advanced[Qwen3-30B-A3B-Qwen3/Qwen3-30B-A3B]
 test_e2e.py::test_ptp_quickstart_bert[TRTLLM-BertForSequenceClassification-bert/bert-base-uncased-yelp-polarity]
 test_e2e.py::test_ptp_quickstart_bert[VANILLA-BertForSequenceClassification-bert/bert-base-uncased-yelp-polarity]
 test_e2e.py::test_ptp_quickstart_multimodal[llava-v1.6-mistral-7b-llava-v1.6-mistral-7b-hf-image-False]
-test_e2e.py::test_ptp_quickstart_multimodal[llava-v1.6-mistral-7b-llava-v1.6-mistral-7b-hf-image]
 test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-image-False]
 test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-image-True]
 test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-image-False]
-test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-image]
 test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-video-False]
-test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-video]
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-image-False]
-test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-image]
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-video-False]
-test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-video]
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-image-False]
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-image-True]
-test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-image]
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-video-False]
 test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-video-True]
-test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-video]
 test_e2e.py::test_ptp_scaffolding[DeepSeek-R1-Distill-Qwen-7B-DeepSeek-R1/DeepSeek-R1-Distill-Qwen-7B]
 test_e2e.py::test_ptp_star_attention_example[Llama3.1-8B-BF16-llama-3.1-model/Meta-Llama-3.1-8B]
 test_e2e.py::test_qwen_e2e_cpprunner_large_new_tokens[DeepSeek-R1-Distill-Qwen-1.5B-DeepSeek-R1-Distill-Qwen-1.5B]