-
Notifications
You must be signed in to change notification settings - Fork 6.8k
[v1.x] Add mx2onnx operator support matrix #20139
Conversation
Hey @Zha0q1 , Thanks for submitting the PR
CI supported jobs: [windows-gpu, clang, miscellaneous, website, edge, unix-cpu, sanity, centos-cpu, unix-gpu, windows-cpu, centos-gpu] Note: |
@@ -65,7 +65,7 @@ def __init__(self): | |||
self.output_tensors = [] | |||
|
|||
@staticmethod | |||
def register(op_name, opset_version=11): | |||
def register(op_name, opset_version=12): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why would we change lowest supported version from 11 to 12?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we support onnx >= 1.7 and 1.7 is actually opset 12.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks
add op support matrix to readme.md and a tool to generate the matrix