-
Notifications
You must be signed in to change notification settings - Fork 2.8k
[NPU] Extend functional tests to cover sub-byte element types #32279
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
[NPU] Extend functional tests to cover sub-byte element types #32279
Conversation
src/plugins/intel_npu/tests/functional/internal/backend/zero_tensor_tests.hpp
Outdated
Show resolved
Hide resolved
d7e9f64 to
ed22a18
Compare
|
What about end-to-end tests for such a scenario? |
There are some func tests OVInferRequestCheckTensorPrecision - they only use @pereanub Please have a look into latest update. |
a9f95ac to
72ab1a6
Compare
72ab1a6 to
a7619f8
Compare
Signed-off-by: Stefania Hergane <[email protected]>
Generate model with same type as precision tested, so that set_tensor is called for all tested precisions Signed-off-by: Stefania Hergane <[email protected]>
a7619f8 to
96a0cf4
Compare
Signed-off-by: Stefania Hergane <[email protected]>
96a0cf4 to
4c6572c
Compare
Details:
CopyZeroTensorAndCheckTensorDataTypeto check all supported tensor data types.OVInferRequestIOTensorSetPrecisionTestNPU. Use model with same type as precision tested, so thatset_tensoris called for all tested precisions.Tickets: