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_ptp_quickstart_advanced[Llama3.1-8B-FP4-modelopt-hf-model-hub/Llama-3.1-8B-Instruct-fp4]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-bf16-instruct-llama-3.1-model/Llama-3.1-8B-Instruct]
test_e2e.py::test_ptp_quickstart_advanced[GPT-OSS-20B-gpt_oss/gpt-oss-20b]
test_e2e.py::test_ptp_quickstart_advanced[GPT-OSS-120B-gpt_oss/gpt-oss-120b]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-8b-fp8-Qwen3/nvidia-Qwen3-8B-FP8]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-8b-nvfp4-Qwen3/nvidia-Qwen3-8B-NVFP4]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-8B-bf16-Qwen3/Qwen3-8B]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-14b-fp8-Qwen3/nvidia-Qwen3-14B-FP8]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-14b-nvfp4-Qwen3/nvidia-Qwen3-14B-NVFP4]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-14B-bf16-Qwen3/Qwen3-14B]
test_e2e.py::test_ptp_quickstart_advanced[Phi4-Reasoning-Plus-fp8-nvidia-Phi-4-reasoning-plus-FP8]
test_e2e.py::test_ptp_quickstart_advanced[Phi4-Reasoning-Plus-nvfp4-nvidia-Phi-4-reasoning-plus-NVFP4]
test_e2e.py::test_ptp_quickstart_advanced[Phi-4-reasoning-plus-bf16-Phi-4-reasoning-plus]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-32B-bf16-Qwen3/Qwen3-32B]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-32b-nvfp4-Qwen3/nvidia-Qwen3-32B-NVFP4]
test_e2e.py::test_ptp_quickstart_advanced[Nemotron-Nano-9B-v2-nvfp4-NVIDIA-Nemotron-Nano-9B-v2-NVFP4]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-30B-A3B-Qwen3/Qwen3-30B-A3B]
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-30B-A3B_nvfp4_hf-Qwen3/saved_models_Qwen3-30B-A3B_nvfp4_hf]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.3-70B-FP8-modelopt-hf-model-hub/Llama-3.3-70B-Instruct-fp8]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.3-70B-FP4-modelopt-hf-model-hub/Llama-3.3-70B-Instruct-fp4]

accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_auto_dtype
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_nvfp4
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_cutlass-torch_compile=False]
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_cutlass-torch_compile=True]

test_e2e.py::test_trtllm_benchmark_serving[gpt_oss/gpt-oss-20b]
examples/serve/test_serve.py::test_nemotron3_super_120b_nvfp4
examples/serve/test_serve.py::test_nemotron3_nano_omni_nvfp4[text_reasoning_on]
examples/serve/test_serve.py::test_nemotron3_nano_omni_nvfp4[text_reasoning_off]
examples/serve/test_serve.py::test_nemotron3_nano_omni_nvfp4[text_streaming]
examples/serve/test_serve.py::test_nemotron3_nano_omni_nvfp4[tool_calling]
examples/serve/test_serve.py::test_nemotron3_nano_omni_nvfp4[image]
examples/serve/test_serve.py::test_nemotron3_nano_omni_nvfp4[video]
