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

fix a bunch of XPU UT failures on stock PyTorch 2.7 and 2.8 (#39069)

Browse Source 
* fix a bunch of XPU UT failures on stock PyTorch 2.7 and 2.8

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* qwen3

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* quanto

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* models

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* fix style

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* idefics2

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
This commit is contained in:
Yao Matrix
2025-06-27 20:01:53 +08:00
committed by GitHub
parent cb17103bd5
commit 0106a50a6b
9 changed files with 53 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
tests/models/aria/test_modeling_aria.py
View File

@@ -30,6 +30,7 @@ from transformers import (
)
from transformers.models.idefics3 import Idefics3VisionConfig
from transformers.testing_utils import (
Expectations,
backend_empty_cache,
require_bitsandbytes,
require_torch,
@@ -483,23 +484,26 @@ class AriaForConditionalGenerationIntegrationTest(unittest.TestCase):
device=model.device, dtype=model.dtype
)
EXPECTED_OUTPUT = {
"cpu": [
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n <image>\n USER: What's the difference of two images?\n ASSISTANT:<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The first image features a cute, light-colored puppy sitting on a paved surface with",
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The image shows a young alpaca standing on a grassy hill. The alpaca has",
], # cpu output
"cuda": [
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n <image>\n USER: What's the difference of two images?\n ASSISTANT:<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The first image features a cute, light-colored puppy sitting on a paved surface with",
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The image shows a young alpaca standing on a patch of ground with some dry grass. The",
], # cuda output
"xpu": [
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n <image>\n USER: What's the difference of two images?\n ASSISTANT:<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The first image features a cute, light-colored puppy sitting on a paved surface with",
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The image shows a young alpaca standing on a grassy hill. The alpaca has",
], # xpu output
}
EXPECTED_OUTPUTS = Expectations(
{
("cpu", None): [
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n <image>\n USER: What's the difference of two images?\n ASSISTANT:<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The first image features a cute, light-colored puppy sitting on a paved surface with",
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The image shows a young alpaca standing on a grassy hill. The alpaca has",
],
("cuda", None): [
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n <image>\n USER: What's the difference of two images?\n ASSISTANT:<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The first image features a cute, light-colored puppy sitting on a paved surface with",
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The image shows a young alpaca standing on a patch of ground with some dry grass. The",
],
("xpu", 3): [
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n <image>\n USER: What's the difference of two images?\n ASSISTANT:<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The first image features a cute, light-colored puppy sitting on a paved surface with",
"<|im_start|>user\n<fim_prefix><fim_suffix> <image>\n USER: Describe the image.\n ASSISTANT:<|im_end|>\n <|im_start|>assistant\n The image shows a young alpaca standing on a patch of ground with some dry grass. The",
],
}
) # fmt: skip
EXPECTED_OUTPUT = EXPECTED_OUTPUTS.get_expectation()
generate_ids = model.generate(**inputs, max_new_tokens=20)
outputs = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
self.assertListEqual(outputs, EXPECTED_OUTPUT[model.device.type])
self.assertListEqual(outputs, EXPECTED_OUTPUT)
def test_tokenizer_integration(self):
model_id = "rhymes-ai/Aria"