Fix dynamic argmax/min when select_last_index is set #827
Conversation
This file contains 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
kevinch-nv
force-pushed
the
fix-argmax-min
branch
from
7fddcaa
to
e3a51e1
Compare
Signed-off-by: Kevin Chen <[email protected]>
yuanyao-nv
approved these changes
Apr 5, 2022
rajeevsrao
approved these changes
Apr 5, 2022
kevinch-nv
added a commit
that referenced
this pull request
Apr 29, 2022
Signed-off-by: Kevin Chen <[email protected]>
kevinch-nv
added a commit
that referenced
this pull request
Nov 1, 2022
* support protobuf >= 3.11 (#812) Signed-off-by: George Wu <[email protected]> * missed other sections for supporting >= protobuf 3.11 (#817) * missed one other section for supporting >= protobuf 3.11 Signed-off-by: George Wu <[email protected]> * one more section Signed-off-by: George Wu <[email protected]> * fix ident Signed-off-by: George Wu <[email protected]> * Update REAMDEs to reflect master -> main rename (#820) Signed-off-by: Kevin Chen <[email protected]> * Fix dynamic argmax/min when select_last_index is set (#827) Signed-off-by: Kevin Chen <[email protected]> * Fix GEMM importer (#828) Signed-off-by: Kevin Chen <[email protected]> * Add support for DisentangledAttentionPlugin (#836) Signed-off-by: Kevin Chen <[email protected]> * TensorRT 8.4 GA ONNX Parser Release (#851) * TensorRT 8.4 EA ONNX Parser Release * support protobuf >= 3.11 (#812) Signed-off-by: George Wu <[email protected]> * missed other sections for supporting >= protobuf 3.11 (#817) * missed one other section for supporting >= protobuf 3.11 Signed-off-by: George Wu <[email protected]> * one more section Signed-off-by: George Wu <[email protected]> * fix ident Signed-off-by: George Wu <[email protected]> * TensorRT 8.4-GA ONNX Parser Release * TensorRT 8.4.1.5 updates (#849) Signed-off-by: Rajeev Rao <[email protected]> Co-authored-by: George Wu <[email protected]> Co-authored-by: Rajeev Rao <[email protected]> * Bug fix: decode error_string if necessary. (#859) Signed-off-by: SimengLiu-nv <[email protected]> * ONNX-TensorRT 22.08 release (#866) Signed-off-by: Kevin Chen <[email protected]> * Update TensorRT version to 8.4.3 (#867) Signed-off-by: Kevin Chen <[email protected]> Signed-off-by: Kevin Chen <[email protected]> * Do not import potential nulltensor for size input in Resize nodes (#871) Signed-off-by: Kevin Chen <[email protected]> Signed-off-by: George Wu <[email protected]> Signed-off-by: Kevin Chen <[email protected]> Signed-off-by: SimengLiu-nv <[email protected]> Co-authored-by: George Wu <[email protected]> Co-authored-by: Rajeev Rao <[email protected]> Co-authored-by: Simeng Liu <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Use shape tensor semantics to do the index conversion in order to support dynamic shapes