We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent e81c50d commit ed7b2f5Copy full SHA for ed7b2f5
tests/integration/test_lists/test-db/l0_dgx_h100.yml
@@ -77,7 +77,8 @@ l0_dgx_h100:
77
backend: pytorch
78
auto_trigger: deepseek
79
tests:
80
- - unittest/_torch/multi_gpu_modeling -k "deepseek"
+ - unittest/_torch/multi_gpu_modeling/test_deepseek.py::test_deepseek_streaming[tp1-bf16-trtllm-deepseekv3_lite]
81
+ - unittest/_torch/multi_gpu_modeling/test_deepseek.py::test_deepseek_streaming[tp4-bf16-trtllm-deepseekv3_lite]
82
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[DeepEP]
83
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[DeepEPLowLatency]
84
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_w4afp8[MoEWeightLoadingMode.VANILLA-dtype0]
0 commit comments