Age | Commit message (Collapse) | Author |
|
* Add supported ops in SupportLibrary
* Removed tableofcontents which was never used
* Separated pages for serializer and deserializer
* Removed link to delegate/IntegrateDelegateIntoPython.md which was removed
* Arranged components in alphabetical order
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ic7a62d0af092f97c49f8ace1a8f8f31d9152b3f8
|
|
- Remove Bf16ToFp32 Conversion Layer
- Remove Fp32ToBf16 Conversion Layer
- Remove B16 Conversion tests
* Throw exception if m_ReduceFp32ToBf16 optimzer option is set to true
* Provide comments to enable fast math in order to use bf16
* Update docs to inform users to enable fast math for bf16
Execute Network Changes
* Require bf16_turbo_mode to also have fast_math_enabled set to true
- Remove setting m_ReduceFp32ToBf16 optimizer option
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ibaa6da9d29c96a1ce32ff5196b0847fde9f04a1c
|
|
* Add a breakdown of the runtime options to the documentation.
* Exclude test classes from Doxygen generation.
* Limit the file extension selection for Doxygen generation.
* Add the support library to be generated.
* Fix some broken markups.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I81896f2d7fff503a1d51d6d4ac3876aa8b84118e
|