Skip to content

Remove BF16 CPU from valid GQA configuration #1469

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
kunal-vaishnavi merged 1 commit into from
May 9, 2025
+1 −2
Merged

Remove BF16 CPU from valid GQA configuration #1469

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 1 addition & 2 deletions src/python/py/models/builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -333,7 +333,6 @@ def make_outputs_init(self):
def make_attention_init(self):
valid_gqa_configurations = [
("cpu", TensorProto.FLOAT),
("cpu", TensorProto.BFLOAT16),
("cuda", TensorProto.FLOAT16),
("cuda", TensorProto.BFLOAT16),
("rocm", TensorProto.FLOAT16),
Expand Down Expand Up @@ -3716,7 +3715,7 @@ def get_args():
)

args = parser.parse_args()
print("Valid precision + execution provider combinations are: FP32 CPU, FP32 CUDA, FP16 CUDA, FP16 DML, BF16 CPU, BF16 CUDA, INT4 CPU, INT4 CUDA, INT4 DML, INT4 WEBGPU")
print("Valid precision + execution provider combinations are: FP32 CPU, FP32 CUDA, FP16 CUDA, FP16 DML, BF16 CUDA, INT4 CPU, INT4 CUDA, INT4 DML, INT4 WEBGPU")
return args

if __name__ == '__main__':
Expand Down