kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][ci] Waive some intermittent failures (#7955)

Browse Source 
Signed-off-by: Hui Gao <huig@nvidia.com>
This commit is contained in:
HuiGao-NV 2025-09-24 19:00:38 +08:00 committed by GitHub
parent cfbcf9b9e8
commit c8bda4b3a9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/integration/test_lists/waives.txt
View File

@ -345,3 +345,9 @@ accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp8_tp2pp2_manage_weights SKIP
accuracy/test_cli_flow.py::TestLlama3_1_8B::test_tp4[enable_gemm_allreduce_plugin] SKIP (https://nvbugs/5532023)
accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_tp2cp2 SKIP (https://nvbugs/5532023)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput_mtp_trtllm] SKIP (https://nvbugs/5537738)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=2-tp2pp2-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5503479)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency] SKIP (https://nvbugs/5523974)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[throughput_tp8] SKIP (https://nvbugs/5523974)
accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[latency_moe_trtllm_attention_dp] SKIP (https://nvbugs/5523974)
accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_bf16[multi_gpus_no_cache] SKIP (https://nvbugs/5523974)
unittest/_torch/modeling/test_modeling_mllama.py::TestMLlama::test_mllama_allclose_to_hf_text_only[backend:flashinfer-use_cuda_graph:False] SKIP (https://nvbugs/5458945)