Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Test PR #1

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Test PR #1

wants to merge 1 commit into from

Conversation

ptrendx
Copy link
Owner

@ptrendx ptrendx commented Oct 7, 2022

No description provided.

Signed-off-by: Przemek Tredak <[email protected]>
@ptrendx ptrendx force-pushed the main branch 6 times, most recently from e4e2198 to 22ef367 Compare October 27, 2022 23:48
ptrendx pushed a commit that referenced this pull request Jan 26, 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 <[email protected]>

* fixes for pylint tests

Signed-off-by: Asfiya Baig <[email protected]>

* fix pylint warning in softmax.py

Signed-off-by: Asfiya Baig <[email protected]>

* move FP8 ORT lib inside tests/

Signed-off-by: Asfiya Baig <[email protected]>

* enable cross attention tests

Signed-off-by: Asfiya Baig <[email protected]>

* 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 <[email protected]>

* fix merge conflict changes

Signed-off-by: Asfiya Baig <[email protected]>

* fix Q/DQ scale input

Signed-off-by: Asfiya Baig <[email protected]>

* enable FP16 config when bias is disabled

Signed-off-by: Asfiya Baig <[email protected]>

* fix pylint check errors

Signed-off-by: Asfiya Baig <[email protected]>

* 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 <[email protected]>

* minor fix: coding guidelines

Signed-off-by: Asfiya Baig <[email protected]>

* changes:
1. skip FP8 tests on  non-hopper devices
2. minor fix for C++ lint check

Signed-off-by: Asfiya Baig <[email protected]>

* fix onnxruntime version

Signed-off-by: Asfiya Baig <[email protected]>

* minor fix: add space between code and comment

Signed-off-by: Asfiya Baig <[email protected]>

* changes
1. update copyrights
2. update path to ORT .so

Signed-off-by: Asfiya Baig <[email protected]>

* Apply suggestions from code review

Co-authored-by: Kirthi Shankar Sivamani <[email protected]>
Signed-off-by: asfiyab-nvidia <[email protected]>

Signed-off-by: Asfiya Baig <[email protected]>
Signed-off-by: asfiyab-nvidia <[email protected]>
Co-authored-by: Kirthi Shankar Sivamani <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant