diff --git a/tests/integration/defs/examples/test_mistral.py b/tests/integration/defs/examples/test_mistral.py index b7f4b3ccce..2e0314ad4c 100644 --- a/tests/integration/defs/examples/test_mistral.py +++ b/tests/integration/defs/examples/test_mistral.py @@ -20,7 +20,7 @@ import psutil import pytest from defs.common import (convert_weights, quantize_data, test_multi_lora_support, venv_check_call) -from defs.conftest import skip_pre_ada +from defs.conftest import skip_post_blackwell, skip_pre_ada from defs.trt_test_alternative import check_call @@ -58,6 +58,7 @@ def mistral_example_root(llm_venv): check_call(" ".join(install_cmd), shell=True, env=llm_venv._new_env) +@skip_post_blackwell #nvbug 5298661 @pytest.mark.parametrize( "run_type", ['inference', 'summarization_long', 'chunked_summarization_long']) diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 640f8745db..209b82b90c 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -50,7 +50,6 @@ full:B200_PCIe/examples/test_mamba.py::test_llm_mamba_1gpu[mamba2-130m-float16-d full:B200_PCIe/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-enable_gemm_plugin] SKIP (Disable for Blackwell) full:B200_PCIe/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-disable_gemm_plugin] SKIP (Disable for Blackwell) full:B200_PCIe/examples/test_medusa.py::test_llm_medusa_1gpu[use_cpp_session-medusa-vicuna-7b-v1.3-4-heads-bfloat16-bs1] SKIP (Disable for Blackwell) -full:B200_PCIe/examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-summarization_long] SKIP (Disable for Blackwell) full:B200_PCIe/examples/test_llama.py::test_llm_llama_v2_1gpu_gemm_swiglu[llama-v2-7b-hf-fp8-float16] SKIP (Disable for Blackwell) full:B200_PCIe/examples/test_llama.py::test_llm_llama_int8_kv_1gpu_summary[llama-7b-enable_weight_only-nb:4] SKIP (Disable for Blackwell) full:B200_PCIe/examples/test_llama.py::test_llm_llama_int8_sq_ootb_1gpu_summary[llama-7b-nb:1] SKIP (Disable for Blackwell) @@ -125,7 +124,6 @@ full:B200/examples/test_mamba.py::test_llm_mamba_1gpu[mamba2-130m-float16-disabl full:B200/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-enable_gemm_plugin] SKIP (Disable for Blackwell) full:B200/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-disable_gemm_plugin] SKIP (Disable for Blackwell) full:B200/examples/test_medusa.py::test_llm_medusa_1gpu[use_cpp_session-medusa-vicuna-7b-v1.3-4-heads-bfloat16-bs1] SKIP (Disable for Blackwell) -full:B200/examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-summarization_long] SKIP (Disable for Blackwell) full:B200/examples/test_llama.py::test_llm_llama_v2_1gpu_gemm_swiglu[llama-v2-7b-hf-fp8-float16] SKIP (Disable for Blackwell) full:B200/examples/test_llama.py::test_llm_llama_int8_kv_1gpu_summary[llama-7b-enable_weight_only-nb:4] SKIP (Disable for Blackwell) full:B200/examples/test_llama.py::test_llm_llama_int8_sq_ootb_1gpu_summary[llama-7b-nb:1] SKIP (Disable for Blackwell) @@ -427,7 +425,7 @@ test_e2e.py::test_ptp_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1- 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) -examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-summarization_long] SKIP (https://nvbugs/5324976) +test_e2e.py::test_openai_reasoning SKIP (https://nvbugs/5310329) accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=False] SKIP (https://nvbugs/5322354) accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=True] SKIP (https://nvbugs/5322354) accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False] SKIP (https://nvbugs/5322354)