phi2 contrib ops changes #19112
Merged
phi2 contrib ops changes #19112
Conversation
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
wangyems
commented
Jan 13, 2024
yufenglee
reviewed
Jan 19, 2024
YUNQIUGUO
pushed a commit
that referenced
this pull request
Jan 23, 2024
### Description <!-- Describe your changes. --> 1. support causal mask in MHA cpu 2. support custom rotary_dim in rotary_emb 3. add bf16 for rotary_emb 4. fix a bug in attention rotary ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->
YUNQIUGUO
pushed a commit
that referenced
this pull request
Jan 30, 2024
### Description This PR updates the Whisper export with beam search by adding the following. - Fixes a bug when running `DecoderMaskedMultiHeadAttention` in the Whisper with beam search model - Sets the default PyTorch attention implementation to `eager` to allow existing attention fusions to continue working - Re-uses the cache directory when loading the PyTorch model to reduce memory used on disk - Adds `--disable_auto_mixed_precision` to the example FP16 export command ### Motivation and Context - [This PR](#19112) added the `is_unidirectional` parameter to `CheckInputs`, but it was not provided when checking the inputs in `DecoderMaskedMultiHeadAttention`. - [This PR](#19200) explains the reasoning behind why `eager` is used to load the `WhisperAttention` class. - By re-using the cache directory for loading the PyTorch model, only one copy of the PyTorch model is saved on disk instead of two copies. - By providing this flag, there will be less Cast nodes in the Whisper with beam search model to switch between FP16 and FP32 precision.
YUNQIUGUO
pushed a commit
that referenced
this pull request
Jan 30, 2024
### Description This PR updates the Whisper export with beam search by adding the following. - Fixes a bug when running `DecoderMaskedMultiHeadAttention` in the Whisper with beam search model - Sets the default PyTorch attention implementation to `eager` to allow existing attention fusions to continue working - Re-uses the cache directory when loading the PyTorch model to reduce memory used on disk - Adds `--disable_auto_mixed_precision` to the example FP16 export command ### Motivation and Context - [This PR](#19112) added the `is_unidirectional` parameter to `CheckInputs`, but it was not provided when checking the inputs in `DecoderMaskedMultiHeadAttention`. - [This PR](#19200) explains the reasoning behind why `eager` is used to load the `WhisperAttention` class. - By re-using the cache directory for loading the PyTorch model, only one copy of the PyTorch model is saved on disk instead of two copies. - By providing this flag, there will be less Cast nodes in the Whisper with beam search model to switch between FP16 and FP32 precision.
rohan11235813
pushed a commit
to quadric-io/onnxruntime
that referenced
this pull request
Aug 19, 2025
### Description This PR updates the Whisper export with beam search by adding the following. - Fixes a bug when running `DecoderMaskedMultiHeadAttention` in the Whisper with beam search model - Sets the default PyTorch attention implementation to `eager` to allow existing attention fusions to continue working - Re-uses the cache directory when loading the PyTorch model to reduce memory used on disk - Adds `--disable_auto_mixed_precision` to the example FP16 export command ### Motivation and Context - [This PR](microsoft/onnxruntime#19112) added the `is_unidirectional` parameter to `CheckInputs`, but it was not provided when checking the inputs in `DecoderMaskedMultiHeadAttention`. - [This PR](microsoft/onnxruntime#19200) explains the reasoning behind why `eager` is used to load the `WhisperAttention` class. - By re-using the cache directory for loading the PyTorch model, only one copy of the PyTorch model is saved on disk instead of two copies. - By providing this flag, there will be less Cast nodes in the Whisper with beam search model to switch between FP16 and FP32 precision.
Contributor
|
This PR has been cherry-picked into the |
rohan11235813
pushed a commit
to quadric-io/onnxruntime
that referenced
this pull request
Sep 15, 2025
### Description This PR updates the Whisper export with beam search by adding the following. - Fixes a bug when running `DecoderMaskedMultiHeadAttention` in the Whisper with beam search model - Sets the default PyTorch attention implementation to `eager` to allow existing attention fusions to continue working - Re-uses the cache directory when loading the PyTorch model to reduce memory used on disk - Adds `--disable_auto_mixed_precision` to the example FP16 export command ### Motivation and Context - [This PR](microsoft/onnxruntime#19112) added the `is_unidirectional` parameter to `CheckInputs`, but it was not provided when checking the inputs in `DecoderMaskedMultiHeadAttention`. - [This PR](microsoft/onnxruntime#19200) explains the reasoning behind why `eager` is used to load the `WhisperAttention` class. - By re-using the cache directory for loading the PyTorch model, only one copy of the PyTorch model is saved on disk instead of two copies. - By providing this flag, there will be less Cast nodes in the Whisper with beam search model to switch between FP16 and FP32 precision.
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.
Description
Motivation and Context