Delegate ModelExpress loading to package (#24723)

Signed-off-by: Zheng Luo <zheluo@nvidia.com>
This commit is contained in:
Zheng Luo
2026-05-16 11:16:44 -07:00
committed by GitHub
parent 0be539024f
commit 435ea41cf0
7 changed files with 60 additions and 503 deletions
@@ -123,6 +123,24 @@ class TestRunaiModelStreamerLoader(CustomTestCase):
self.assertIsInstance(model_loader, loader_mod.RunaiModelStreamerLoader)
def test_get_model_loader_uses_remote_instance_for_prequantized_modelopt(self):
load_config = LoadConfig(
load_format=LoadFormat.REMOTE_INSTANCE,
model_loader_extra_config={},
)
model_config = cast(
ModelConfig,
SimpleNamespace(
quantization="modelopt_fp4",
modelopt_quant=False,
_is_already_quantized=lambda: True,
),
)
model_loader = loader_mod.get_model_loader(load_config, model_config)
self.assertIsInstance(model_loader, loader_mod.RemoteInstanceModelLoader)
if __name__ == "__main__":
unittest.main()