You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "lhutton1 (via GitHub)" <gi...@apache.org> on 2023/08/04 13:52:47 UTC
[GitHub] [tvm] lhutton1 commented on a diff in pull request #15407: [CMSIS-NN] Support for Softmax Int16 operator
lhutton1 commented on code in PR #15407:
URL: https://github.com/apache/tvm/pull/15407#discussion_r1284453363
##########
tests/python/contrib/test_cmsisnn/test_softmax.py:
##########
@@ -91,6 +91,50 @@ def test_op_int8(zero_point, scale, compiler_cpu, cpu_flags):
)
+@skip_if_no_reference_system
+@tvm.testing.requires_cmsisnn
+@pytest.mark.parametrize(["zero_point", "scale"], [[0, 1.0 / 32768]])
+@pytest.mark.parametrize(
+ "compiler_cpu, cpu_flags", [("cortex-m55", "+nomve"), ("cortex-m55", ""), ("cortex-m7", "")]
+)
+def test_op_int16(zero_point, scale, compiler_cpu, cpu_flags):
Review Comment:
@Nikeran and I discussed this and came to the same conclusion, will mark as resolved, thanks!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org