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

waive test_moe.py::test_moe_fp8[autotune] (#5455)

Browse Source 
Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com>
This commit is contained in:
QI JUN 2025-06-25 09:14:44 +08:00 committed by GitHub
parent 699520082b
commit 241f921800
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/unittest/_torch/thop/test_moe.py
View File

@ -579,7 +579,8 @@ def quant_dequant_per_tensor_fp8(a):
ids=["autotune", "no_autotune"])
def test_moe_fp8(num_tokens, expert_info, hidden_size, intermediate_size,
use_autotune):
if use_autotune:
pytest.skip("https://nvbugs/5356427")
torch.random.manual_seed(0)
#