Fuse MatMulInteger and scale followed#4350
Merged
Conversation
tracysh
reviewed
Jun 30, 2020
| .TypeConstraint( | ||
| "T1", | ||
| {"tensor(int8)", "tensor(uint8)"}, | ||
| "Constrain input B data type to 8-bit integer tensor.") |
Contributor
There was a problem hiding this comment.
This is input A, right? Should the type constraints use the same "input 'A'" (single quoted) style as above? #Resolved
tracysh
reviewed
Jun 30, 2020
| "of elements should be equal to the number of columns of input 'B'.", | ||
| "T2", | ||
| OpSchema::Optional) | ||
| .Input(6, |
Contributor
There was a problem hiding this comment.
run clang-format? the input seems to be indented oddly. should the 6 be on the next line to match the style from your other ops? #Resolved
tracysh
reviewed
Jun 30, 2020
|
|
||
| const Tensor* a_scale_tensor = ctx->Input<Tensor>(2); | ||
| ORT_ENFORCE(IsScalarOr1ElementVector(a_scale_tensor), | ||
| "MatmulInteger : input A scale must be a scalar or 1D tensor of size 1. Per-Channel is not supported yet."); |
Contributor
There was a problem hiding this comment.
fixup operator name? #Resolved
yufenglee
force-pushed
the
roli/matmul-integer
branch
from
092344a to
9961f58
Compare
skottmckay
reviewed
Jul 2, 2020
skottmckay
reviewed
Jul 2, 2020
skottmckay
reviewed
Jul 2, 2020
skottmckay
reviewed
Jul 2, 2020
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description: Describe your changes.
Fuse MatMulInteger + scale + bias followed
Add bias for DynamicQuantizeMatMul