-
Notifications
You must be signed in to change notification settings - Fork 117
Update build and test script and dockerfile to add in onnxrt pai laun… #4336
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
Conversation
ahsan-ca
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good. A minor nit: The name of the PR exceeds the limit allowed and has spilled over to the description. It would be good to fix this for readability of commits in the history. Thanks!
|
[2025-09-29T22:53:27.271Z] [----------] Global test environment tear-down |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR updates the ONNX Runtime integration by copying PAI launcher scripts to ONNX Runtime to enable script reuse from prior runs, addressing a related change from a previous PR.
- Modified the build script to handle copying PAI launcher scripts with silent error handling in CI environments
- Updated the ONNX Runtime commit reference to a newer version
- Added PAI launcher scripts directly to the Docker image for better integration
Reviewed Changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| tools/build_and_test_onnxrt.sh | Added silent error handling for copying PAI scripts in CI environments |
| test/onnx/.onnxrt-commit | Updated ONNX Runtime commit hash to newer version |
| Dockerfile | Added PAI launcher scripts directly to the Docker image build |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
|
copilot error handling suggestion is worthwhile to include |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## develop #4336 +/- ##
========================================
Coverage 92.25% 92.25%
========================================
Files 559 559
Lines 26218 26218
========================================
Hits 24185 24185
Misses 2033 2033 🚀 New features to boost your workflow:
|
* [7.1] Resolve Bert and Inception quick tune * Update build and test script and dockerfile to add in onnxrt pai laun… (#4336) Update build and test script and dockerfile to add in onnxrt pai launcher scripts Push pai launcher scripts to Onnxrutime to let us reuse scripts from prior run Related to change from - #4321 * resolve merge conflicts --------- Co-authored-by: Ted Themistokleous <107195283+TedThemistokleous@users.noreply.github.com>
* Update build and test script and dockerfile to add in onnxrt pai laun… (#4336) Update build and test script and dockerfile to add in onnxrt pai launcher scripts Push pai launcher scripts to Onnxrutime to let us reuse scripts from prior run Related to change from - #4321 * Bump SQlite3 to 3.50.4 (#4322) * TopK exception bugfix (#4329) * Use --input-dim for specifying dynamic shapes at driver runtime (#4342) * Add video and render groups in docker for CI (#4340) * Fix MXFP4 bugs (#4324) * propagate_constant ignores `unpack_fp4` instructions now * `match_find_mx_quantizable_ops` from `simplify_qdq` updated to not require non-constant scales. The scales can be literals. * transpose, reshape, and broadcast instructions propagated on scale instructions when going to `quant_dot` and `quant_conv` * `raw_data` `operator<<` updated to use `fallback_visit` to also handle non-computable types * Brevitas MXFP4 quantization parse (#4301) * Bump onnx to 1.18.0 (#4323) * Fuse GEMM+GEMM with rocMLIR (#4261) rocmlir supports GEMM+GEMM fusion, so MIGraphX needs to support the fusion on our side. Solves #4230 * Updated SD3 example for change in optimum-onnx[onnxruntime] (#4344) * Lower lrn to pooling (#4294) This PR implements a lowering transformation that converts LRN operations into a series of pooling and arithmetic operations. * Update onnxruntime main be655f69f6c8623eebcac094626d0c8545951e6d (#4348) * Update docs/reference/MIGraphX-dev-env-vars.rst --------- Co-authored-by: Ted Themistokleous <107195283+TedThemistokleous@users.noreply.github.com> Co-authored-by: Lakhinder Walia <139581206+lakhinderwalia@users.noreply.github.com> Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com> Co-authored-by: Charlie Lin <charlie.lin@amd.com> Co-authored-by: Breanna Devore-McDonald <breanna.devore-mcdonald@amd.com> Co-authored-by: Aarushi Jain <142941703+aarushjain29@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
…cher scripts
Motivation
Push pai launcher scripts to Onnxrutime to let us reuse scripts from prior run
Related to change from - #4321
Technical Details
Copy the pai scripts from tools directory and use them in our CI when invoking the Dockerfile
Changelog Category