[ONNX] Add Onnx->Torch lowering for GroupQueryAttention op #4006
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add Torch->Linalg for rotary embedding Add lowering for rotary embedding - rough patch Add check inputs to rot_emb lowering Add test for rotary embedding Rebase fix
This commit adds the lowering for Onnx's GroupQueryAttention op. The lowering is adopted from here: https://github.com/microsoft/onnxruntime/blob/65008cbb7393b121400a40dd8af4cc93d506918f/onnxruntime/contrib_ops/cpu/bert/group_query_attention.cc#L45 The lowering supports the GQA with rotary_embedding. Signed-off-by: Vivek Khandelwal <[email protected]>
|
This PR also contains the commit for Rotary_embedding since the lowering need that. I will remove it from this PR, once this PR #4002 is merged. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This commit adds the lowering for Onnx's GroupQueryAttention op.
The lowering is adopted from here: https://github.com/microsoft/onnxruntime/blob/65008cbb7393b121400a40dd8af4cc93d506918f/onnxruntime/contrib_ops/cpu/bert/group_query_attention.cc#L45
The lowering supports the GQA with rotary_embedding.
Signed-off-by: Vivek Khandelwal [email protected]