Skip to content

Commit 9d2af4c

Browse files
cccclaifacebook-github-bot
authored andcommitted
backout the schema definition change (#3213)
Summary: Pull Request resolved: #3213 The schame was changed to avoid double register, but it was hiding the symptons by using a differnt schema. Resume the correct the schema Reviewed By: larryliu0820 Differential Revision: D56432559 fbshipit-source-id: d9d0a92a6c6fa04857ea01916647eb46ed658849
1 parent 9769386 commit 9d2af4c

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

kernels/quantized/quantized.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,7 @@
4040
- arg_meta: null
4141
kernel_name: torch::executor::quantized_embedding_byte_out
4242

43-
- func: quantized_decomposed::embedding_byte.dtype_out(Tensor weight, Tensor weight_scales, Tensor? weight_zero_points, int weight_quant_min, int weight_quant_max, Tensor indices, ScalarType? dtype=None, *, Tensor(a!) out) -> Tensor(a!)
43+
- func: quantized_decomposed::embedding_byte.dtype_out(Tensor weight, Tensor weight_scales, Tensor? weight_zero_points, int weight_quant_min, int weight_quant_max, Tensor indices, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!)
4444
variants: function
4545
kernels:
4646
- arg_meta: null

0 commit comments

Comments
 (0)