[Model Loading] Overlap checkpoint staging with CUDA graph capture during startup (#32017)
Co-authored-by: Wenhui Zhu <wzhu59@asu.edu> Co-authored-by: Alex Nails <alex.nails@radixark.ai>
This commit is contained in:
co-authored by
Wenhui Zhu
Alex Nails
parent
0772e79ee7
commit
6b94d39f13
@@ -93,6 +93,25 @@ class TestServerArgsAnnotatedCli(CustomTestCase):
|
||||
sa = self._parse(["--image-processor-backend", backend])
|
||||
self.assertEqual(sa.image_processor_backend, backend)
|
||||
|
||||
def test_startup_weight_load_mode(self):
|
||||
"""The startup loading mode keeps serial as the safe default."""
|
||||
serial = self._parse([])
|
||||
overlap = self._parse(["--startup-weight-load-mode", "overlap"])
|
||||
self.assertEqual(serial.startup_weight_load_mode, "serial")
|
||||
self.assertFalse(serial.is_startup_weight_load_overlap)
|
||||
self.assertEqual(overlap.startup_weight_load_mode, "overlap")
|
||||
self.assertTrue(overlap.is_startup_weight_load_overlap)
|
||||
|
||||
with self.assertRaises(SystemExit):
|
||||
self.parser.parse_args(
|
||||
[
|
||||
"--model",
|
||||
"dummy",
|
||||
"--startup-weight-load-mode",
|
||||
"unsupported",
|
||||
]
|
||||
)
|
||||
|
||||
def test_deprecated_flags_still_work(self):
|
||||
"""Deprecated flags set the correct dest field."""
|
||||
sa = self._parse(["--stream-output"])
|
||||
|
||||
Reference in New Issue
Block a user