[CPU] SparseAttention op #21110
[CPU] SparseAttention op #21110
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
There was a problem hiding this comment.
PREfast found more than 20 potential problems in the proposed changes. Check the Files changed tab for more details.
| @@ -0,0 +1,321 @@ | |||
| // Copyright (c) Microsoft Corporation. All rights reserved. | |||
Check warning
Code scanning / lintrunner
CLANGFORMAT/format Warning
| @@ -0,0 +1,210 @@ | |||
| // Copyright (c) Microsoft Corporation. All rights reserved. | |||
Check warning
Code scanning / lintrunner
CLANGFORMAT/format Warning
| sequence_length = sequence_lengths[i % len(sequence_lengths)] | ||
| num_heads = heads[i % len(heads)] | ||
| head_size = head_sizes[i % len(head_sizes)] | ||
| format = formats[i % len(formats)] |
Check warning
Code scanning / CodeQL
Variable defined multiple times Warning
| def get_test_cases(provider: str, has_past_kv:bool, comprehensive: bool, debug=False): | ||
| if provider == "CUDAExecutionProvider" and not has_cuda_support(): | ||
| return | ||
| yield |
Check warning
Code scanning / CodeQL
Unreachable code Warning
Description
Add SparseAttention cpu implementation. It depends on CPU Flash Attention in #20805.
This work is still in progress:
Motivation and Context