Skip to content

Enable bf16x3, bf16x6 for dot input precisions #5403

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

Merged
merged 2 commits into from
Oct 29, 2025
Merged

Enable bf16x3, bf16x6 for dot input precisions #5403

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f5c1464
Enable bf16x3, bf16x6 for dot input precisions
dev-tomek Oct 29, 2025
4c720f3
Merge branch 'main' into tkuczynski/dot_with_bf16x3_bf16x6
dev-tomek Oct 29, 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
2 changes: 0 additions & 2 deletions python/test/unit/language/test_core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3272,8 +3272,6 @@ def test_dot(M, N, K, num_warps, col_a, col_b, epilogue, input_precision, in_dty
pytest.xfail(f"input_precision {input_precision} is not supported in the interpreter")
else:
if is_xpu():
if input_precision in ("bf16x3", "bf16x6"):
pytest.skip(f"input_precision {input_precision} is not supported")
if (M < 8 or N < 16 or (K < 16 and in_dtype == 'float16') or (K < 8 and in_dtype == 'float32')):
pytest.xfail("XPU: small dots are not supported")
elif not is_hip() and K < 16:
Expand Down
2 changes: 1 addition & 1 deletion third_party/intel/backend/compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ class XPUOptions:
supported_fp8_dtypes: Tuple[str] = ("fp8e5", "fp8e4nv", "fp8e4b15")
deprecated_fp8_dot_operand_dtypes: Tuple[str] = ()
default_dot_input_precision: str = "tf32"
allowed_dot_input_precisions: Tuple[str] = ("tf32", "tf32x3", "ieee")
allowed_dot_input_precisions: Tuple[str] = ("tf32", "tf32x3", "ieee", 'bf16x3', 'bf16x6')
allow_fp8e4nv: bool = False
allow_fp8e4b15: bool = True
grf_mode: tuple = ('small', 'large', 'auto', 'default')
Expand Down
Loading