This repository was archived by the owner on Nov 17, 2023. It is now read-only.
[v1.x] Add 1:many conversions in nnvm_to_onnx and non-flatten GEMM#19652
Merged
ptrendx merged 1 commit intoapache:v1.xfrom Jan 5, 2021
Merged
[v1.x] Add 1:many conversions in nnvm_to_onnx and non-flatten GEMM#19652ptrendx merged 1 commit intoapache:v1.xfrom
ptrendx merged 1 commit intoapache:v1.xfrom
Conversation
Signed-off-by: Serge Panev <spanev@nvidia.com>
|
Hey @Kh4L , Thanks for submitting the PR
CI supported jobs: [centos-cpu, website, sanity, clang, unix-cpu, unix-gpu, windows-cpu, windows-gpu, edge, centos-gpu, miscellaneous] Note: |
lanking520
added
pr-awaiting-testing
Kh4L
added a commit
to Kh4L/incubator-mxnet
that referenced
this pull request
Mar 5, 2021
…9652) Signed-off-by: Serge Panev <spanev@nvidia.com>
ptrendx
pushed a commit
that referenced
this pull request
Mar 5, 2021
* Update MXNet-TRT doc with the new optimize_for API Signed-off-by: Serge Panev <spanev@nvidia.com> * [1.x] Move block.optimize_for backend_opts to kwargs (#19386) * Move block.optimize_for backend_opts to kwargs Signed-off-by: Serge Panev <spanev@nvidia.com> * Update Hybridize to use kwargs as backend opts Signed-off-by: Serge Panev <spanev@nvidia.com> * Fix lint Signed-off-by: Serge Panev <spanev@nvidia.com> * Change clear default to False and allow hybrize+optimize_for calls Signed-off-by: Serge Panev <spanev@nvidia.com> * Fix nit Signed-off-by: Serge Panev <spanev@nvidia.com> * Adress review comments Signed-off-by: Serge Panev <spanev@nvidia.com> * Adress more review comments Signed-off-by: Serge Panev <spanev@nvidia.com> * Adress more more review comments Signed-off-by: Serge Panev <spanev@nvidia.com> * Fix nit Signed-off-by: Serge Panev <spanev@nvidia.com> * Add 1:many conversions in nnvm_to_onnx and non-flatten GEMM (#19652) Signed-off-by: Serge Panev <spanev@nvidia.com>
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
4 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
This PR:
flatten=False, which are not supported natively supported by ONNX and TensorRT. It converts the operator to a subgraph composed of Transpose+MatMul+Add ONNX ops.