-
Notifications
You must be signed in to change notification settings - Fork 74k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[oneDNN] QuantizeV2 with bfloat16 Input #66085
base: master
Are you sure you want to change the base?
Conversation
Hi @penpornk Can you please review this PR ? Thank you! |
@cantonios Thanks for reviewing this PR. I have addressed the comments. Please check. |
@@ -21,30 +21,48 @@ limitations under the License. | |||
#include "tensorflow/core/kernels/ops_testutil.h" | |||
#include "tensorflow/core/kernels/ops_util.h" | |||
#include "tensorflow/core/lib/core/status_test_util.h" | |||
#include "tensorflow/core/lib/gtl/array_slice.h" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
tensorflow/core/kernels/quantize_op_test.cc:24:10: error: module //tensorflow/core/kernels:quantize_op_test does not depend on a module exporting 'tensorflow/core/lib/gtl/array_slice.h'
24 | #include "tensorflow/core/lib/gtl/array_slice.h"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Fixed it now. Thanks!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Our dependency checker is failing. See comment above.
@cantonios Is there any other issues with this PR? |
Reopened the closed PR: #56613
This PR depends on #66082
It extends QuantizeV2 op for converting bfloat16 tensor to quantized tensor. It helps quantizing a model with bfloat16 and 8-bit integer mixed precisions, for example using Intel Neural Compressor (INC) tool (https://github.com/intel/neural-compressor).