diff --git a/tests/integration/defs/test_e2e.py b/tests/integration/defs/test_e2e.py index 94a45937e5e..7b8e122c120 100644 --- a/tests/integration/defs/test_e2e.py +++ b/tests/integration/defs/test_e2e.py @@ -677,7 +677,7 @@ def temp_extra_llm_api_options_file(request): "enable_block_reuse": False, "max_tokens": 40000 }, - "_num_postprocess_workers": 2, + "num_postprocess_workers": 2, } pytorch_backend_config = {} diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 4a76a98b85c..0c22070850f 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -241,7 +241,6 @@ examples/test_qwen.py::test_llm_qwen_moe_multi_gpu_summary[qwen2_57b_a14b-tp2pp2 examples/test_mixtral.py::test_llm_mixtral_moe_plugin_fp8_lora_4gpus[Mixtral-8x7B-v0.1-chinese-mixtral-lora] SKIP (https://nvbugs/5064768) llmapi/test_llm_e2e.py::test_llmapi_build_command_parameters_align[llama-llama-models-v2/TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5061624) test_e2e.py::test_openai_consistent_chat SKIP (https://nvbugs/5112075) -test_e2e.py::test_trtllm_bench_pytorch_backend_sanity SKIP (https://nvbugs/5345720) full:B200/examples/test_gemma.py::test_llm_hf_gemma_quantization_1gpu[gemma-2-9b-it-fp8-bfloat16-8] SKIP (not supported on B200) full:B200/examples/test_gpt.py::test_llm_gpt2_starcoder_1gpus SKIP (not supported on B200) examples/test_medusa.py::test_mistral_medusa_1gpu[mistral-7b-v0.1] SKIP (https://nvbugs/5137575)