Large page size aligned hierarchical caching (#4581)

This commit is contained in:
Zhiqiang Xie
2025-04-01 22:38:15 -07:00
committed by GitHub
parent 9eb49e878b
commit e119f04215
8 changed files with 242 additions and 71 deletions

View File

@@ -21,7 +21,10 @@ class TestHierarchicalMLA(CustomTestCase):
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=["--trust-remote-code", "--enable-hierarchical-cache"],
other_args=[
"--trust-remote-code",
"--enable-hierarchical-cache",
],
)
@classmethod