fix memory for online fp8 quantization with streaming weight load (#31914)
Signed-off-by: vasiliy <vasiliy@fb.com>
This commit is contained in:
@@ -25,4 +25,4 @@ class DummyModelLoader(BaseModelLoader):
|
||||
def load_weights(self, model: nn.Module, model_config: ModelConfig) -> None:
|
||||
# NOTE(woosuk): For accurate performance evaluation, we assign
|
||||
# random values to the weights.
|
||||
initialize_dummy_weights(model)
|
||||
initialize_dummy_weights(model, model_config)
|
||||
|
||||
Reference in New Issue
Block a user