chore: fix typo in tests (#5092)

Signed-off-by: Fanrong Li <[email protected]>

Author: lfr-0531

tests/integration/defs/.test_durations

@@ -294,7 +294,7 @@
    "test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]": 81.43792725296225,
    "test_e2e.py::test_ptp_quickstart_advanced_eagle3[Llama-3.1-8b-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct-EAGLE3-LLaMA3.1-Instruct-8B]": 109.26379436196294,
    "test_e2e.py::test_ptp_quickstart_advanced_mixed_precision": 80.88908524392173,
-   "test_e2e.py::test_ptq_quickstart_advanced_mtp[DeepSeek-V3-Lite-BF16-DeepSeek-V3-Lite/bf16]": 99.42739840806462,
+   "test_e2e.py::test_ptp_quickstart_advanced_mtp[DeepSeek-V3-Lite-BF16-DeepSeek-V3-Lite/bf16]": 99.42739840806462,
    "test_unittests.py::test_unittests_v2[unittest/_torch/speculative/test_eagle3.py]": 317.8708840459585,
    "accuracy/test_cli_flow.py::TestLlama7B::test_auto_dtype": 402.75543826818466,
    "examples/test_bert.py::test_llm_bert_general[compare_hf-disable_remove_input_padding-disable_attention_plugin-disable_context_fmha-tp:1-pp:1-float32-BertModel-bert/bert-base-uncased]": 111.17977902293205,

tests/integration/defs/test_e2e.py

@@ -1601,7 +1601,7 @@ def test_ptp_quickstart_advanced(llm_root, llm_venv, model_name, model_path):
 @pytest.mark.parametrize("model_name,model_path", [
     ("DeepSeek-V3-Lite-BF16", "DeepSeek-V3-Lite/bf16"),
 ])
-def test_ptq_quickstart_advanced_mtp(llm_root, llm_venv, model_name,
+def test_ptp_quickstart_advanced_mtp(llm_root, llm_venv, model_name,
                                      model_path):
     print(f"Testing {model_name}.")
     example_root = Path(os.path.join(llm_root, "examples", "pytorch"))
@@ -1626,7 +1626,7 @@ def test_ptq_quickstart_advanced_mtp(llm_root, llm_venv, model_name,
 
 
 @pytest.mark.skip_less_device(4)
-def test_ptq_quickstart_advanced_bs1(llm_root, llm_venv):
+def test_ptp_quickstart_advanced_bs1(llm_root, llm_venv):
     model_name = "DeepSeek-V3-Lite-FP8"
     model_path = "DeepSeek-V3-Lite/fp8"
     print(f"Testing {model_name}.")
@@ -1653,7 +1653,7 @@ def test_ptq_quickstart_advanced_bs1(llm_root, llm_venv):
 @pytest.mark.parametrize("model_name,model_path", [
     ("Llama-3.1-8B-Instruct", "llama-3.1-model/Llama-3.1-8B-Instruct"),
 ])
-def test_ptq_quickstart_advanced_ngram(llm_root, llm_venv, model_name,
+def test_ptp_quickstart_advanced_ngram(llm_root, llm_venv, model_name,
                                        model_path):
     print(f"Testing {model_name}.")
     example_root = Path(os.path.join(llm_root, "examples", "pytorch"))

tests/integration/test_lists/qa/examples_test_list.txt

@@ -508,7 +508,7 @@ test_e2e.py::test_ptp_quickstart_advanced[Llama3.2-11B-BF16-llama-3.2-models/Lla
 test_e2e.py::test_ptp_quickstart_advanced[Nemotron4_4B-BF16-nemotron/Minitron-4B-Base]
 test_e2e.py::test_ptp_quickstart_advanced[Nemotron-H-8B-Nemotron-H-8B-Base-8K]
 test_e2e.py::test_ptp_quickstart_advanced[Qwen3-30B-A3B-Qwen3/Qwen3-30B-A3B]
-test_e2e.py::test_ptq_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct]
+test_e2e.py::test_ptp_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct]
 test_e2e.py::test_ptp_quickstart_advanced_8gpus[Llama3.1-70B-BF16-llama-3.1-model/Meta-Llama-3.1-70B]
 test_e2e.py::test_ptp_quickstart_advanced_8gpus[Llama3.1-70B-FP8-llama-3.1-model/Llama-3.1-70B-Instruct-FP8]
 test_e2e.py::test_ptp_quickstart_advanced_8gpus[Llama3.1-405B-FP8-llama-3.1-model/Llama-3.1-405B-Instruct-FP8]

tests/integration/test_lists/test-db/l0_b200.yml

@@ -44,7 +44,7 @@ l0_b200:
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_trtllm]
   - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
   - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]
-  - test_e2e.py::test_ptq_quickstart_advanced_mtp[DeepSeek-V3-Lite-BF16-DeepSeek-V3-Lite/bf16]
+  - test_e2e.py::test_ptp_quickstart_advanced_mtp[DeepSeek-V3-Lite-BF16-DeepSeek-V3-Lite/bf16]
   - test_e2e.py::test_ptp_quickstart_advanced_mixed_precision
   - test_e2e.py::test_ptp_quickstart_advanced_eagle3[Llama-3.1-8b-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct-EAGLE3-LLaMA3.1-Instruct-8B]
   - test_e2e.py::test_trtllm_bench_pytorch_backend_sanity[meta-llama/Llama-3.1-8B-llama-3.1-8b-False-False]

tests/integration/test_lists/test-db/l0_dgx_h100.yml

@@ -38,7 +38,7 @@ l0_dgx_h100:
   - disaggregated/test_disaggregated.py::test_disaggregated_overlap[TinyLlama-1.1B-Chat-v1.0]
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[False]
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[True]
-  - test_e2e.py::test_ptq_quickstart_advanced_bs1
+  - test_e2e.py::test_ptp_quickstart_advanced_bs1
 - condition:
     ranges:
       system_gpu_count:

tests/integration/test_lists/waives.txt

@@ -423,7 +423,7 @@ accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype
 accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[True] SKIP (https://nvbugs/5303573)
 test_e2e.py::test_openai_multi_chat_example SKIP (https://nvbugs/5236980)
 test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-70B-FP8-llama-3.1-model/Llama-3.1-70B-Instruct-FP8] SKIP (https://nvbugs/5318059)
-test_e2e.py::test_ptq_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct] SKIP (https://nvbugspro.nvidia.com/bug/5324239)
+test_e2e.py::test_ptp_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct] SKIP (https://nvbugspro.nvidia.com/bug/5324239)
 unittest/_torch/auto_deploy/integration/test_ad_build.py SKIP (https://nvbugs/5318103)
 accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=TRTLLM-torch_compile=False] SKIP (https://nvbugs/5318143)
 accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=TRTLLM-torch_compile=True] SKIP (https://nvbugs/5318143)