[0.11.0][Bugfix]fix_mulit_connector_bug (#3332) (#3882)

### What this PR does / why we need it?
When using multi connector, the multi connector does not define
get_finished_count, which will cause the kv cache to be released ###
Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.11.0rc3
- vLLM main:
83f478bb19


Signed-off-by: baxingpiaochong <771405853@qq.com>
Co-authored-by: baxingpiaochong <771405853@qq.com>
This commit is contained in:
fems14
2025-10-29 23:44:52 +08:00
committed by GitHub
parent e5b938c5fe
commit 19f49ecb5f
2 changed files with 9 additions and 41 deletions

View File

@@ -667,10 +667,6 @@ class TestMooncakeConnectorSchedulerMatchedTokens(unittest.TestCase):
self.assertEqual(meta.requests["req1"].remote_block_ids, [1, 2, 3])
self.assertEqual(len(self.scheduler._reqs_need_recv), 0)
def test_get_finished_count(self):
count = self.scheduler.get_finished_count()
self.assertEqual(count, 2)
class TestHelperFunctions(unittest.TestCase):