update: Update MSFT Contrib Ops in OVEP#521
Conversation
|
@ankitm3k, Can you please test a few models with these custom ops and ensure only the backends/ devices that are functional are called out as supported. |
63560cc to
562d1fc
Compare
8d43b06 to
562d1fc
Compare
|
Modified data_ops.cc to remove unsupported ops, namely: SkipSimplifiedLayerNormalization This PR adds support for: Attention |
a53fa99 to
c8ba719
Compare
7f2ff4f to
a98fc3e
Compare
c8ba719 to
b5b8e5a
Compare
a6698ce to
84fd325
Compare
b5b8e5a to
b727038
Compare
|
Spreadsheet used in testing the various operators: https://intel-my.sharepoint.com/:x:/p/ankit_maheshkar/EeMj4cZ-2XNEpoWznBgtKc8B6f7oKR9uZjlWNKUH0VYqdg?e=dihHPM |
b727038 to
e1027cc
Compare
e43cdb3 to
fb6bdee
Compare
e1027cc to
e8e3a18
Compare
cd89be3 to
ade3b59
Compare
|
@ankitm3k PR is unblocked Please rebase, review and ready to merge |
c045197 to
935c8db
Compare
27b5c23 to
875d055
Compare
LGTM. Reviewed it |
|
LGTM |
* update: Update MSFT Contrib Ops from OV * modified data_ops.cc to remove unsupported ops * disabled tests for EmbedLayerNormalisation and MatMulNBits --------- Co-authored-by: n1harika <[email protected]>
* update: Update MSFT Contrib Ops from OV * modified data_ops.cc to remove unsupported ops * disabled tests for EmbedLayerNormalisation and MatMulNBits --------- Co-authored-by: n1harika <[email protected]>
* Internal ci for PTL 1.1 (#523) * update: Update MSFT Contrib Ops in OVEP (#521) * update: Update MSFT Contrib Ops from OV * modified data_ops.cc to remove unsupported ops * disabled tests for EmbedLayerNormalisation and MatMulNBits --------- Co-authored-by: n1harika <[email protected]> * Add Max op to no_dimension_supported list --------- Co-authored-by: jatinwadhwa921 <[email protected]> Co-authored-by: Ankit Maheshkar <[email protected]> Co-authored-by: n1harika <[email protected]>
* update: Update MSFT Contrib Ops from OV * modified data_ops.cc to remove unsupported ops * disabled tests for EmbedLayerNormalisation and MatMulNBits --------- Co-authored-by: n1harika <[email protected]>
* Internal ci for PTL 1.1 (#523) * update: Update MSFT Contrib Ops in OVEP (#521) * update: Update MSFT Contrib Ops from OV * modified data_ops.cc to remove unsupported ops * disabled tests for EmbedLayerNormalisation and MatMulNBits --------- Co-authored-by: n1harika <[email protected]> * Add Max op to no_dimension_supported list --------- Co-authored-by: jatinwadhwa921 <[email protected]> Co-authored-by: Ankit Maheshkar <[email protected]> Co-authored-by: n1harika <[email protected]>
* update: Update MSFT Contrib Ops from OV * modified data_ops.cc to remove unsupported ops * disabled tests for EmbedLayerNormalisation and MatMulNBits --------- Co-authored-by: n1harika <[email protected]>
* Internal ci for PTL 1.1 (#523) * update: Update MSFT Contrib Ops in OVEP (#521) * update: Update MSFT Contrib Ops from OV * modified data_ops.cc to remove unsupported ops * disabled tests for EmbedLayerNormalisation and MatMulNBits --------- Co-authored-by: n1harika <[email protected]> * Add Max op to no_dimension_supported list --------- Co-authored-by: jatinwadhwa921 <[email protected]> Co-authored-by: Ankit Maheshkar <[email protected]> Co-authored-by: n1harika <[email protected]>
Description
This PR Updates the latest OV supported Contrib Ops in OVEP