diff --git a/tests/integration/defs/agg_unit_mem_df.csv b/tests/integration/defs/agg_unit_mem_df.csv index 5f9cf79953..19aa90460c 100644 --- a/tests/integration/defs/agg_unit_mem_df.csv +++ b/tests/integration/defs/agg_unit_mem_df.csv @@ -120,3 +120,4 @@ unittest/kv_cache_manager_v2_tests/,NVIDIA B200,8, unittest/_torch/attention,NVIDIA H100,4, unittest/_torch/misc,NVIDIA H100,4, unittest/_torch/thop/parallel,NVIDIA H100,16, +unittest/_torch/flashinfer/test_trtllm_flashinfer_symbol_collision.py,NVIDIA H100 PCIe,1, diff --git a/tests/integration/test_lists/test-db/l0_h100.yml b/tests/integration/test_lists/test-db/l0_h100.yml index 4a5b4b4219..80b2635162 100644 --- a/tests/integration/test_lists/test-db/l0_h100.yml +++ b/tests/integration/test_lists/test-db/l0_h100.yml @@ -27,6 +27,7 @@ l0_h100: - unittest/_torch/speculative -k "not eagle3" - unittest/_torch/thop/parallel - unittest/_torch/thop/serial + - unittest/_torch/flashinfer/test_trtllm_flashinfer_symbol_collision.py # Only key models in H100: llama/mixtral/nemotron/deepseek - unittest/_torch/modeling -k "modeling_llama" - unittest/_torch/modeling -k "modeling_mixtral" diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 0e1170db81..409fb1822c 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -280,7 +280,6 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mt accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=2-tp4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/5800672) examples/test_ray.py::test_llm_inference_distributed_ray[tp2pp2] SKIP (https://nvbugs/5781731) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/5800646) -unittest/_torch/attention/test_trtllm_flashinfer_symbol_collision.py::test_flashinfer_fused_moe_matches_torch_moe SKIP (https://nvbugs/5814215) full:sm89/accuracy/test_llm_api_pytorch_multimodal.py::TestNVILA_8B::test_auto_dtype SKIP (https://nvbugs/5814504) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-tp2pp2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/5819005) unittest/llmapi/test_mpi_session.py::test_llmapi_launch_multiple_tasks SKIP (https://nvbugs/5819014) diff --git a/tests/unittest/_torch/attention/test_trtllm_flashinfer_symbol_collision.py b/tests/unittest/_torch/flashinfer/test_trtllm_flashinfer_symbol_collision.py similarity index 100% rename from tests/unittest/_torch/attention/test_trtllm_flashinfer_symbol_collision.py rename to tests/unittest/_torch/flashinfer/test_trtllm_flashinfer_symbol_collision.py