[CI/Build] Improve Tensor Schema tests speed by avoid engine core initialization (#23357)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
@@ -209,7 +209,7 @@ class OvisImagePatchInputs(TypedDict):
|
||||
`(batch_size * num_patches, patch_size_x * patch_size_y * num_channels)`
|
||||
"""
|
||||
|
||||
inducator_tokens: torch.Tensor
|
||||
indicator_tokens: torch.Tensor
|
||||
"""
|
||||
Shape:
|
||||
`(batch_size * (num_patches + 1))`
|
||||
|
||||
Reference in New Issue
Block a user