[main] flashcomm_v1 optim in Qwen Dense Models (#2802)

### What this PR does / why we need it?
Flashcomm_v1 optim in Qwen Dense Models.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.1.1
- vLLM main:
5e537f45b4

Co-authored-by: 1024daniel <xxltju324@gmail.com>
This commit is contained in:
rjg-lyh
2025-09-08 22:52:24 +08:00
committed by GitHub
parent 4df8df5b94
commit 1bbb20ea13
11 changed files with 362 additions and 20 deletions

View File

@@ -303,13 +303,13 @@ class TestUtils(TestBase):
# ascend custom op is not registered
utils.register_ascend_customop()
# should call register_oot three
self.assertEqual(mock_customop.register_oot.call_count, 12)
self.assertEqual(mock_customop.register_oot.call_count, 13)
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 three in this ut
self.assertEqual(mock_customop.register_oot.call_count, 12)
self.assertEqual(mock_customop.register_oot.call_count, 13)
class TestProfileExecuteDuration(TestBase):