EngineX-Ascend/enginex-ascend-910-vllm
10
0
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity

init v0.11.0rc0

Browse Source
This commit is contained in:
luopingyi
2025-10-14 10:38:28 +08:00
parent 67afd0ea78
commit 66dc16f966
278 changed files with 28130 additions and 11708 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
tests/ut/torchair/test_utils.py
View File

@@ -6,7 +6,6 @@ from unittest.mock import MagicMock, patch
import torch
from tests.ut.base import TestBase
from vllm_ascend.quantization.quantizer import SUPPORT_ASCEND_QUANTIZER_TYPE
from vllm_ascend.torchair import utils
@@ -135,15 +134,3 @@ class TestTorchairUtils(TestBase):
utils.converting_weight_acl_format(model, ACL_FORMAT_FRACTAL_NZ)
mock_npu_cast.assert_not_called()
def test_torchair_quant_method_register(self):
TorchairW8A8DYNAMICQuantizer = SUPPORT_ASCEND_QUANTIZER_TYPE[
"W8A8_DYNAMIC"]
TorchairW4A8DYNAMICQuantizer = SUPPORT_ASCEND_QUANTIZER_TYPE[
"W4A8_DYNAMIC"]
utils.torchair_quant_method_register()
self.assertNotEqual(TorchairW8A8DYNAMICQuantizer,
SUPPORT_ASCEND_QUANTIZER_TYPE["W8A8_DYNAMIC"])
self.assertNotEqual(TorchairW4A8DYNAMICQuantizer,
SUPPORT_ASCEND_QUANTIZER_TYPE["W4A8_DYNAMIC"])