Add bfloat16 to all relevant ops #6099
Conversation
thiagocrepaldi
added
auto update doc
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. |
thiagocrepaldi
added
auto update doc
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| #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
thiagocrepaldi
removed
the
auto update doc
Signed-off-by: Thiago Crepaldi <thiagofc@microsoft.com>
thiagocrepaldi
force-pushed
the
thiagofc/fix-3842
branch
from
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