You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/04/06 18:27:23 UTC
[GitHub] [tvm] mbrookhart opened a new pull request #7802: [ONNX] Initial work to import pre-quantized ONNX Models
mbrookhart opened a new pull request #7802:
URL: https://github.com/apache/tvm/pull/7802
This PR implements QuantlizeLinear, DequantizeLinear, and DynamicQuantizeLinear (which is deprecated but included for completeness).
--
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] mbrookhart commented on a change in pull request #7802: [ONNX] Initial work to import pre-quantized ONNX Models
Posted by GitBox <gi...@apache.org>.
mbrookhart commented on a change in pull request #7802:
URL: https://github.com/apache/tvm/pull/7802#discussion_r608123715
##########
File path: tests/python/frontend/onnx/test_forward.py
##########
@@ -4165,15 +4165,8 @@ def verify_cumsum(indata, axis, exclusive=0, reverse=0, type="float32"):
"test_cumsum_2d_axis_0/",
"test_cumsum_2d_axis_1/",
"test_cumsum_2d_negative_axis/",
- "test_dequantizelinear/",
Review comment:
Yes, we're running all of the pre-serialized node tests that ship with ONNX against CPU now, except what's skipped in this list. Working on reducing what we skip, and I'll start enabling GPU soon.
--
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] masahi commented on pull request #7802: [ONNX] Initial work to import pre-quantized ONNX Models
Posted by GitBox <gi...@apache.org>.
masahi commented on pull request #7802:
URL: https://github.com/apache/tvm/pull/7802#issuecomment-814576795
thanks @mbrookhart @jwfromm
--
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] masahi merged pull request #7802: [ONNX] Initial work to import pre-quantized ONNX Models
Posted by GitBox <gi...@apache.org>.
masahi merged pull request #7802:
URL: https://github.com/apache/tvm/pull/7802
--
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] masahi commented on a change in pull request #7802: [ONNX] Initial work to import pre-quantized ONNX Models
Posted by GitBox <gi...@apache.org>.
masahi commented on a change in pull request #7802:
URL: https://github.com/apache/tvm/pull/7802#discussion_r608119953
##########
File path: tests/python/frontend/onnx/test_forward.py
##########
@@ -4165,15 +4165,8 @@ def verify_cumsum(indata, axis, exclusive=0, reverse=0, type="float32"):
"test_cumsum_2d_axis_0/",
"test_cumsum_2d_axis_1/",
"test_cumsum_2d_negative_axis/",
- "test_dequantizelinear/",
Review comment:
Do we run these tests on CI?
--
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org