diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index a56816ea4832..13ceaecceba4 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -6253,7 +6253,14 @@ def test_fp8(self, enable_block_reuse, mocker): kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.8, enable_block_reuse=enable_block_reuse) - moe_config = MoeConfig(backend='DEEPGEMM') + # DeepGEMM MoE kernels only support datacenter Blackwell (SM100/SM103). + # Fall back to the CUTLASS MoE backend (which supports FP8 block scales) + # on other architectures such as Hopper (SM90) and consumer Blackwell + # (SM120/SM121); otherwise the unsupported kernel trips a scale-factor + # dtype assertion at warmup. + moe_backend = "DEEPGEMM" if get_sm_version() in (100, + 103) else "CUTLASS" + moe_config = MoeConfig(backend=moe_backend) cuda_graph_config = CudaGraphConfig(enable_padding=True, max_batch_size=128) with LLM(model_dir, diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 9237ef23835d..b998772df193 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -130,7 +130,6 @@ accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_fp8[throughput_laten accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention_4gpus[target_sparsity_0.5-fp8kv=False] SKIP (https://nvbugs/6260915) accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention_4gpus[target_sparsity_0.5-fp8kv=True] SKIP (https://nvbugs/6248783) accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention_4gpus[target_sparsity_0.9-fp8kv=False] SKIP (https://nvbugs/6260915) -accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8[enable_block_reuse=False] SKIP (https://nvbugs/6212252) accuracy/test_llm_api_pytorch.py::TestQwen3_5_397B_A17B::test_nvfp4[tep4_cutedsl] SKIP (https://nvbugs/6255417) accuracy/test_llm_api_pytorch.py::TestQwen3_5_9B::test_bf16[mtp_off] SKIP (https://nvbugs/6212250) accuracy/test_llm_api_pytorch.py::TestQwen3_5_9B::test_bf16[mtp_on] SKIP (https://nvbugs/6212250)