SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update expected values (after switching to A10) - part 4 (#39189)

Browse Source 
* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar
2025-07-03 15:13:06 +02:00
committed by GitHub
parent b31e9d19a6
commit a25fc3592e
25 changed files with 298 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
tests/models/mixtral/test_modeling_mixtral.py
View File

@@ -191,27 +191,26 @@ class MixtralIntegrationTest(unittest.TestCase):
# ("cuda", 8) for A100/A10, and ("cuda", 7) for T4.
#
# considering differences in hardware processing and potential deviations in generated text.
# fmt: off
EXPECTED_LOGITS_LEFT_UNPADDED = Expectations(
{
("xpu", 3): torch.Tensor([[0.2236, 0.5195, -0.3828], [0.8203, -0.2295, 0.6055], [0.2676, -0.7070, 0.2461]]).to(torch_device),
("cuda", 7): torch.Tensor([[0.2236, 0.5195, -0.3828], [0.8203, -0.2275, 0.6054], [0.2656, -0.7070, 0.2460]]).to(torch_device),
("cuda", 8): torch.Tensor([[0.2207, 0.5234, -0.3828], [0.8203, -0.2285, 0.6055], [0.2656, -0.7109, 0.2451]]).to(torch_device),
("rocm", 9): torch.Tensor([[0.2236, 0.5195, -0.3828], [0.8203, -0.2285, 0.6055], [0.2637, -0.7109, 0.2451]]).to(torch_device),
("xpu", 3): [[0.2236, 0.5195, -0.3828], [0.8203, -0.2295, 0.6055], [0.2676, -0.7070, 0.2461]],
("cuda", 7): [[0.2236, 0.5195, -0.3828], [0.8203, -0.2275, 0.6054], [0.2656, -0.7070, 0.2460]],
("cuda", 8): [[0.2217, 0.5195, -0.3828], [0.8203, -0.2295, 0.6055], [0.2676, -0.7109, 0.2461]],
("rocm", 9): [[0.2236, 0.5195, -0.3828], [0.8203, -0.2285, 0.6055], [0.2637, -0.7109, 0.2451]],
}
)
expected_left_unpadded = EXPECTED_LOGITS_LEFT_UNPADDED.get_expectation()
expected_left_unpadded = torch.tensor(EXPECTED_LOGITS_LEFT_UNPADDED.get_expectation(), device=torch_device)
EXPECTED_LOGITS_RIGHT_UNPADDED = Expectations(
{
("xpu", 3): torch.Tensor([[0.2178, 0.1270, -0.1641], [-0.3496, 0.2988, -1.0312], [0.0693, 0.7930, 0.8008]]).to(torch_device),
("cuda", 7): torch.Tensor([[0.2167, 0.1269, -0.1640], [-0.3496, 0.2988, -1.0312], [0.0688, 0.7929, 0.8007]]).to(torch_device),
("cuda", 8): torch.Tensor([[0.2178, 0.1270, -0.1621], [-0.3496, 0.3008, -1.0312], [0.0693, 0.7930, 0.7969]]).to(torch_device),
("rocm", 9): torch.Tensor([[0.2197, 0.1250, -0.1611], [-0.3516, 0.3008, -1.0312], [0.0684, 0.7930, 0.8008]]).to(torch_device),
("xpu", 3): [[0.2178, 0.1270, -0.1641], [-0.3496, 0.2988, -1.0312], [0.0693, 0.7930, 0.8008]],
("cuda", 7): [[0.2167, 0.1269, -0.1640], [-0.3496, 0.2988, -1.0312], [0.0688, 0.7929, 0.8007]],
("cuda", 8): [[0.2178, 0.1260, -0.1621], [-0.3496, 0.2988, -1.0312], [0.0693, 0.7930, 0.8008]],
("rocm", 9): [[0.2197, 0.1250, -0.1611], [-0.3516, 0.3008, -1.0312], [0.0684, 0.7930, 0.8008]],
}
)
expected_right_unpadded = EXPECTED_LOGITS_RIGHT_UNPADDED.get_expectation()
# fmt: on
expected_right_unpadded = torch.tensor(EXPECTED_LOGITS_RIGHT_UNPADDED.get_expectation(), device=torch_device)
with torch.no_grad():
logits = model(dummy_input, attention_mask=attention_mask).logits