diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py b/tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py index e0f7c4b17ec4..9b79a69196b9 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py @@ -545,6 +545,7 @@ class TestKimiK25(LlmapiAccuracyTestHarness): preserve_caller_max_tokens=True, ) + @pytest.mark.timeout(7200) @skip_pre_blackwell @pytest.mark.skip_less_mpi_world_size(8) @pytest.mark.skip_less_device_memory(183000) diff --git a/tests/integration/test_lists/qa/llm_function_core.txt b/tests/integration/test_lists/qa/llm_function_core.txt index 2a4262426c18..fd23de69cc1f 100644 --- a/tests/integration/test_lists/qa/llm_function_core.txt +++ b/tests/integration/test_lists/qa/llm_function_core.txt @@ -789,7 +789,7 @@ accuracy/test_llm_api_pytorch_encode.py::TestEncoderEncode::test_qwen3_text_embe accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] accuracy/test_llm_api_pytorch_multimodal.py::TestGemma3_27BInstruct::test_fp8_prequantized -accuracy/test_llm_api_pytorch_multimodal.py::TestKimiK25::test_nvfp4[dep8] +accuracy/test_llm_api_pytorch_multimodal.py::TestKimiK25::test_nvfp4[dep8] TIMEOUT (120) accuracy/test_llm_api_pytorch_multimodal.py::TestMistralLarge3_675B::test_nvfp4_4gpus[latency_moe_trtllm] accuracy/test_llm_api_pytorch_multimodal.py::TestMistralSmall24B::test_auto_dtype[forced_chunked_prefill] accuracy/test_llm_api_pytorch_multimodal.py::TestNanoV3Omni::test_auto_dtype[bf16] diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 13cec4c43895..5462b117b0bf 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -148,7 +148,6 @@ full:B200/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_8gpu full:B200/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_dummy_load_format SKIP (https://nvbugs/6525059) full:B200/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6597570) full:B200/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6597570) -full:B200/accuracy/test_llm_api_pytorch_multimodal.py::TestKimiK25::test_nvfp4[dep8] SKIP (https://nvbugs/6626655) full:B200/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-glm5_nvfp4_tp4_ep4_dp_stress] SKIP (https://nvbugs/6544407) full:B200/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_multi_lora_varying_ranks[cudagraph] SKIP (https://nvbugs/6475623) full:B200/test_e2e.py::test_multi_nodes_eval[Qwen3/Qwen3-235B-A22B-tp16-mmlu] SKIP (https://nvbugs/6424188) @@ -169,7 +168,6 @@ full:B300/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_dummy_load_f full:B300/accuracy/test_llm_api_pytorch.py::TestStep3_7::test_fp8_block_scales[tp_size=4-ep_size=4-mtp_nextn=3] SKIP (https://nvbugs/6539941) full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6597570) full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6597570) -full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestKimiK25::test_nvfp4[dep8] SKIP (https://nvbugs/6626655) full:B300/disaggregated/test_disaggregated.py::test_disaggregated_logprobs_serving[llama-3.1-8b-instruct] SKIP (https://nvbugs/6275959) full:B300/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_multi_lora_varying_ranks[cudagraph] SKIP (https://nvbugs/6475623) full:B300/unittest/_torch/attention/test_attention_backends.py::test_attention_backend[qwen2_0_5b_gqa_hd64-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6610548)