Merged
Conversation
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
ksivaman
added a commit
that referenced
this pull request
Jan 18, 2023
* Add ONNX export support for TE modules (#1) * Add TorchScript Operators * Add symbolic methods to ONNX exporter * Add tests for the ONNX export Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * fixes for pylint tests Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * fix pylint warning in softmax.py Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * move FP8 ORT lib inside tests/ Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * enable cross attention tests Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * refactor code by @nzmora * Increase layernorm FP16 threshold * Normalize onnx file names: _ separates configs; - separates words in a single config * Add get_attn_mask_str and fix mask string * Add missing ONNX files * Moved generated ONNX files to tests/gen_onnx_models/ Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * fix merge conflict changes Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * fix Q/DQ scale input Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * enable FP16 config when bias is disabled Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * fix pylint check errors Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * updates 1. remove List import for pylint failure 2. address comments: remove state tensors from GPU 3. address comments: Update reverse_map_dtype function and add to namespace Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * minor fix: coding guidelines Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * changes: 1. skip FP8 tests on non-hopper devices 2. minor fix for C++ lint check Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * fix onnxruntime version Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * minor fix: add space between code and comment Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * changes 1. update copyrights 2. update path to ORT .so Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> * Apply suggestions from code review Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com> Signed-off-by: asfiyab-nvidia <117682710+asfiyab-nvidia@users.noreply.github.com> Signed-off-by: Asfiya Baig <asfiyab@nvidia.com> Signed-off-by: asfiyab-nvidia <117682710+asfiyab-nvidia@users.noreply.github.com> Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
11 tasks
13 tasks
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
1 participant
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.
Signed-off-by: Przemek Tredak ptredak@nvidia.com