This PR upgrade CANN from 8.2rc1 to 8.3rc1 and remove the CANN version
check logic.
TODO: we notice that UT runs failed with CANN 8.3 image. So the base
image for UT is still 8.2. We'll fix it later.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
@@ -63,33 +63,20 @@ class TestAscendUnquantizedLinearMethod(TestBase):
|
||||
|
||||
@mock.patch("vllm_ascend.ops.linear.is_enable_nz")
|
||||
@mock.patch("torch_npu.npu_format_cast")
|
||||
@mock.patch("torch.version")
|
||||
def test_process_weights_after_loading_is_8_3_enable_nz(
|
||||
self, mock_version, mock_format_cast, mock_is_nz):
|
||||
mock_version.cann = "8.3.RC1"
|
||||
def test_process_weights_after_loading_enable_nz(self, mock_format_cast,
|
||||
mock_is_nz):
|
||||
mock_is_nz.return_value = 1
|
||||
self.method.process_weights_after_loading(self.layer)
|
||||
mock_format_cast.assert_called_once()
|
||||
|
||||
@mock.patch("vllm_ascend.ops.linear.is_enable_nz")
|
||||
@mock.patch("torch_npu.npu_format_cast")
|
||||
@mock.patch("torch.version")
|
||||
def test_process_weights_after_loading_is_8_3_disable_nz(
|
||||
self, mock_version, mock_format_cast, mock_is_nz):
|
||||
mock_version.cann = "8.3.RC1"
|
||||
def test_process_weights_after_loading_disable_nz(self, mock_format_cast,
|
||||
mock_is_nz):
|
||||
mock_is_nz.return_value = 0
|
||||
self.method.process_weights_after_loading(self.layer)
|
||||
mock_format_cast.assert_not_called()
|
||||
|
||||
@mock.patch("vllm_ascend.ops.linear.is_enable_nz")
|
||||
@mock.patch("torch.version")
|
||||
def test_process_weights_after_loading_not_8_3(self, mock_version,
|
||||
mock_is_nz):
|
||||
mock_version.cann = "8.2.RC1"
|
||||
mock_is_nz.return_value = 1
|
||||
# Should not raise exception
|
||||
self.method.process_weights_after_loading(self.layer)
|
||||
|
||||
|
||||
class TestAscendRowParallelLinear(BaseLinearTest):
|
||||
|
||||
|
||||
Reference in New Issue
Block a user