Enable RMS_NORM and VIEW in OpenVINO backend, remove op_case 2 for rope#153
Open
zhaixuejun1993 wants to merge 4 commits into
Open
Enable RMS_NORM and VIEW in OpenVINO backend, remove op_case 2 for rope#153zhaixuejun1993 wants to merge 4 commits into
zhaixuejun1993 wants to merge 4 commits into
Conversation
Collaborator
|
Cannot verify currently since dev_backend_openvino is broken for gemma4 due to a previous change: 335cf5c |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 pull request makes targeted adjustments to the OpenVINO backend integration in the
ggmlproject, focusing on refining operator handling and improving the logic for tensor output detection. The changes enhance the accuracy and reliability of operator identification and backend support checks.Operator handling improvements:
GgmlOvDecoder::compute_op_caseto no longer set a specific bit for nodes whose first source is aVIEWoperation, simplifying the operator case determination process.is_output_idxstatic method inGgmlOvDecoderto additionally check that the second source tensor's operation isGGML_OP_NONE, making output index detection more precise.Backend support adjustments:
GGML_OP_RMS_NORMfrom the set of operations that are not supported with aVIEWinput in the OpenVINO backend, potentially enabling new operation combinations.