[1/N][CustomOp] Register activation customop instead of overwrite forward_oot (#1841)

### What this PR does / why we need it?
We'll refator `CustomOp` in vllm-ascend from this pr on. 

Use function `CustomOp.register_oot` to achieve the customop registery,
taking `AscendQuickGELU` as an example:
```python
from vllm_ascend.ops.activation import AscendQuickGELU
CustomOp.register_oot(_decorated_op_cls=AscendQuickGELU, name="QuickGELU")
```

This is a quick adapt for `CustomOp.register_oot` mechanism from vllm
0.9.2. For further step, we can remove inherit from `QuickGELU` can
write our own `QuickGELU` at all.

Part of https://github.com/vllm-project/vllm-ascend/pull/1647



- vLLM version: v0.9.2
- vLLM main:
8dfb45ca33

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-07-18 23:07:14 +08:00
committed by GitHub
parent 8a91e6e59c
commit 574fe407eb
8 changed files with 154 additions and 22 deletions

View File

@@ -301,6 +301,24 @@ class TestUtils(TestBase):
self.assertFalse(utils.check_kv_cache_bytes_cache_exist(),
"Delete kv cache bytes cache dir failed")
@mock.patch("vllm.model_executor.custom_op.CustomOp")
@mock.patch("vllm_ascend.ops.activation.AscendQuickGELU")
@mock.patch("vllm_ascend.ops.activation.AscendSiluAndMul")
def test_register_ascend_customop(self, mock_ascend_silu_and_mul,
mock_ascend_quick_gelu, mock_customop):
utils._ASCEND_CUSTOMOP_IS_REIGISTERED = False
# ascend custom op is not registered
utils.register_ascend_customop()
# should call register_oot twice
self.assertEqual(mock_customop.register_oot.call_count, 2)
self.assertTrue(utils._ASCEND_CUSTOMOP_IS_REIGISTERED)
# ascend custom op is already registered
utils.register_ascend_customop()
# should not register_oot again, thus only called twice in this ut
self.assertEqual(mock_customop.register_oot.call_count, 2)
class TestProfileExecuteDuration(unittest.TestCase):