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 unittest/trt/model/test_mamba.py::TestMamba::test_loaders_mamba_130m_hf_from_checkpoint. Will fix it later. (#3356)

Browse Source 
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
This commit is contained in:
Fanrong Li 2025-04-08 13:36:35 +08:00 committed by GitHub
parent 31422e7e46
commit 62e0876e39
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/unittest/trt/model/test_mamba.py
View File

@ -366,6 +366,11 @@ class TestMamba(unittest.TestCase):
pytest.skip(f'Skipping since the path {hf_path} does not exist.')
dtype = 'float16'
if path == 'mamba-130m-hf' and load_mode == 'from_checkpoint':
pytest.skip(
f'Skipping since it is a known issue. Will be fixed in the near future.'
)
# get hf mamba
hf_mamba = AutoModelForCausalLM.from_pretrained(
hf_path, device_map='cpu', torch_dtype=str_dtype_to_torch(dtype))