Skip to content

[DRAFT] Add basic test for GQA (fusion) #2142

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.

Sign up for GitHub

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

Closed
gramalingam wants to merge 11 commits into from
Closed

[DRAFT] Add basic test for GQA (fusion) #2142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
0bc603f
Basic GQA test
gramalingam Mar 25, 2025
794f0dd
Minor refactoring
gramalingam Mar 27, 2025
a7ba01b
Switch to script
gramalingam Mar 27, 2025
d68b0e7
Add blank line
gramalingam Mar 27, 2025
e535207
Merge branch 'main' into rama/gqa-basic-test
gramalingam Mar 27, 2025
df5c69d
Add test case with past and rotary
gramalingam Mar 28, 2025
045fc6f
Add new test
gramalingam Mar 29, 2025
edf289f
Cleanup test case
gramalingam Mar 29, 2025
457ac32
Added test with past and rotary
gramalingam Mar 29, 2025
1efdb26
Remove debug print
gramalingam Mar 29, 2025
13a71c0
Minor cleanup
gramalingam Mar 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions onnxscript/rewriter/ort_fusions/_test_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,5 +39,8 @@
np.testing.assert_equal(baseline_output.shape, optimized_output.shape)
np.testing.assert_allclose(baseline_output, optimized_output, rtol=rtol, atol=atol)
except AssertionError as e:
diff_mask = ~np.isclose(baseline_output, optimized_output, rtol=rtol, atol=atol)
diff = np.where(diff_mask, "X", " ")
print(diff)

Check warning on line 44 in onnxscript/rewriter/ort_fusions/_test_utils.py

View check run for this annotation

Codecov / codecov/patch

onnxscript/rewriter/ort_fusions/_test_utils.py#L42-L44 

Added lines #L42 - L44 were not covered by tests
print(f"Failed for output {i} with rtol={rtol} and atol={atol}\n{e}")
raise
Loading
Loading