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

enable more test cases on xpu (#38572)

Browse Source 
* enable glm4 integration cases on XPU, set xpu expectation for blip2

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

* more

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

* fix style

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

* refine wording

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

* refine test case names

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

* run

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

* add gemma2 and chameleon

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

* fix review comments

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

---------

Signed-off-by: Matrix YAO <matrix.yao@intel.com>
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
This commit is contained in:
Yao Matrix
2025-06-06 15:29:51 +08:00
committed by GitHub
parent 31023b6909
commit 89542fb81c
23 changed files with 150 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/quantization/bnb/test_mixed_int8.py
View File

@@ -730,7 +730,7 @@ class MixedInt8TestCpuGpu(BaseMixedInt8Test):
output_text = self.tokenizer.decode(output_parallel[0], skip_special_tokens=True)
self.assertIn(output_text, self.EXPECTED_OUTPUTS)
def test_cpu_gpu_loading_random_device_map(self):
def test_cpu_accelerator_loading_random_device_map(self):
r"""
A test to check is dispatching a model on cpu & gpu works correctly using a random `device_map`.
"""
@@ -778,7 +778,7 @@ class MixedInt8TestCpuGpu(BaseMixedInt8Test):
self.check_inference_correctness(model_8bit)
def test_cpu_gpu_loading_custom_device_map(self):
def test_cpu_accelerator_loading_custom_device_map(self):
r"""
A test to check is dispatching a model on cpu & gpu works correctly using a custom `device_map`.
This time the device map is more organized than the test above and uses the abstraction
@@ -805,7 +805,7 @@ class MixedInt8TestCpuGpu(BaseMixedInt8Test):
self.check_inference_correctness(model_8bit)
def test_cpu_gpu_disk_loading_custom_device_map(self):
def test_cpu_accelerator_disk_loading_custom_device_map(self):
r"""
A test to check is dispatching a model on cpu & gpu works correctly using a custom `device_map`.
This time we also add `disk` on the device_map.
@@ -832,7 +832,7 @@ class MixedInt8TestCpuGpu(BaseMixedInt8Test):
self.check_inference_correctness(model_8bit)
def test_cpu_gpu_disk_loading_custom_device_map_kwargs(self):
def test_cpu_accelerator_disk_loading_custom_device_map_kwargs(self):
r"""
A test to check is dispatching a model on cpu & gpu works correctly using a custom `device_map`.
This time we also add `disk` on the device_map - using the kwargs directly instead of the quantization config