kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-14 06:53:50 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Update test name.

Browse Source 
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
This commit is contained in:
Bo Li 2025-12-04 00:14:00 +08:00
parent b210f22c7e
commit e2bc360441
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/integration/test_lists/test-db/l0_dgx_b200.yml
View File

@ -16,7 +16,7 @@ l0_dgx_b200:
orchestrator: mpi
tests:
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[DeepEPLowLatency]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[MNNVL]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[NVLinkTwoSided]
- accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=TRTLLM-torch_compile=False]
- accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp4-fp8kv=True-attn_backend=TRTLLM-torch_compile=False]
- accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True]

2
tests/integration/test_lists/test-db/l0_dgx_h100.yml
View File

@ -127,7 +127,7 @@ l0_dgx_h100:
- unittest/_torch/multi_gpu_modeling/test_deepseek.py::test_deepseek_streaming[tp4-bf16-trtllm-deepseekv3_lite]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[DeepEP]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[DeepEPLowLatency]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[MNNVL]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[NVLinkTwoSided]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_w4afp8[MoEWeightLoadingMode.VANILLA-dtype0]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_w4afp8[MoEWeightLoadingMode.VANILLA-dtype1]
- unittest/_torch/modules/test_fused_moe.py::test_fused_moe_w4afp8[MoEWeightLoadingMode.W4A8_CUSTOM-dtype0]