[CPU] SparseAttention op #21110
Merged
[CPU] SparseAttention op #21110
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
![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.
onnxruntime/test/python/transformers/test_sparse_attention.py
Dismissed
Show dismissed
Hide dismissed
tianleiwu
requested review from
wangyems,
kunal-vaishnavi,
aciddelgado and
yufenglee
kunal-vaishnavi
previously approved these changes
Jul 3, 2024
wangyems
previously approved these changes
Jul 3, 2024
kunal-vaishnavi
approved these changes
Jul 3, 2024
kunal-vaishnavi
added a commit
to microsoft/onnxruntime-genai
that referenced
this pull request
Jul 29, 2024
### Description This PR adds support for building Phi-3 small ONNX models for CPU in the model builder. ### Motivation and Context Previously, the `SparseAttention` operator was only supported on CUDA in ONNX Runtime. With the [recent support](microsoft/onnxruntime#21110) for `SparseAttention` on CPU, Phi-3 small ONNX models can now run on CPU. This PR also helps [this issue](#519). To use these changes, both ONNX Runtime and ONNX Runtime GenAI need to be [built from source](https://onnxruntime.ai/docs/genai/howto/build-from-source.html#option-3-build-from-source). Because the official PyTorch repo does not have a `tokenizer.json` file, the `tokenizer.json` file needed for Phi-3 small in ONNX Runtime GenAI can be downloaded from the Hugging Face repos. Please see [here](https://huggingface.co/microsoft/Phi-3-small-8k-instruct-onnx-cuda/blob/main/cuda-int4-rtn-block-32/tokenizer.json) for Phi-3 small 8K and [here](https://huggingface.co/microsoft/Phi-3-small-128k-instruct-onnx-cuda/blob/main/cuda-int4-rtn-block-32/tokenizer.json) for Phi-3 small 128K.
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
Add SparseAttention cpu implementation.
This is unfused implementation. The flash attention version will be added later.
Motivation and Context