-
Notifications
You must be signed in to change notification settings - Fork 3.6k
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
Add bfloat16 to all relevant ops #6099
Conversation
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #6099 +/- ##
==========================================
+ Coverage 56.95% 57.03% +0.08%
==========================================
Files 506 506
Lines 30467 30935 +468
Branches 4592 4592
==========================================
+ Hits 17353 17645 +292
- Misses 12285 12465 +180
+ Partials 829 825 -4 ☔ View full report in Codecov by Sentry. |
#include "onnx/defs/function.h" | ||
#include "onnx/defs/math/utils.h" | ||
#include "onnx/defs/schema.h" | ||
#include "onnx/defs/tensor_proto_util.h" | ||
|
||
namespace ONNX_NAMESPACE { | ||
|
||
bool BuildContextDependentFunctionBody_opset13( |
Check warning
Code scanning / CodeQL
Poorly documented large function Warning
return {"tensor(float16)", "tensor(float)", "tensor(double)"}; | ||
} | ||
|
||
std::function<void(OpSchema&)> PoolOpSchemaGenerator_opset19( |
Check warning
Code scanning / CodeQL
Poorly documented large function Warning
|
||
ONNX_OPERATOR_SET_SCHEMA(ConvTranspose, 11, OpSchema().FillUsing(ConvTransposeOpSchemaGenerator_opset11("a filter"))); | ||
|
||
std::function<void(OpSchema&)> ConvOpSchemaGenerator_opset11(const char* filter_desc) { |
Check warning
Code scanning / CodeQL
Poorly documented large function Warning
convPoolShapeInference_opset19(ctx, true, false, 0, 1); | ||
})); | ||
|
||
std::function<void(OpSchema&)> ConvTransposeOpSchemaGenerator_opset11(const char* filter_desc) { |
Check warning
Code scanning / CodeQL
Poorly documented large function Warning
} | ||
} | ||
} | ||
std::function<void(OpSchema&)> RNNDocGenerator_opset14(const char* /*name*/) { |
Check warning
Code scanning / CodeQL
Poorly documented large function Warning
Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
1b73c53
to
21c24bc
Compare
everything passing, except the mac errors during python setup stage |
@gramalingam regarding the comment to refactor the test engine to select ir10 instead of test list, can we make this as a follow up? this feature is not strictly related to bfloat16 and this pr is already quite big |
sure, that's fine, thanks! |
Reland onnx#6079 Fixes onnx#3842 Fixes onnx#6071 Fixes onnx#4051 @gramalingam @justinchuby FYI Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com> Signed-off-by: isdanni <leedanni@gmail.com>
Reland onnx#6079 Fixes onnx#3842 Fixes onnx#6071 Fixes onnx#4051 @gramalingam @justinchuby FYI Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com> Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>
Reland onnx#6079 Fixes onnx#3842 Fixes onnx#6071 Fixes onnx#4051 @gramalingam @justinchuby FYI Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com> Signed-off-by: Andreas Fehlner <fehlner@arcor.de>
Reland #6079
Fixes #3842
Fixes #6071
Fixes #4051
@gramalingam @justinchuby FYI