optimize gqa cpu #20598
Merged
optimize gqa cpu #20598
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
tianleiwu
reviewed
May 8, 2024
tianleiwu
reviewed
May 8, 2024
tianleiwu
approved these changes
May 8, 2024
yihonglyu
pushed a commit
that referenced
this pull request
May 9, 2024
### Description <!-- Describe your changes. --> optimize the GQA implementation on CPU. Mainly optimization are: 1. compute attention on real total sequence length instead of maximum sequence length in case past/present share same buffer 2. remove the mask 3. remove the transpose after attention x value It improve the phi3 model https://github.com/microsoft/onnxruntime-genai/blob/main/examples/python/phi3-qa.py with max sequence length 2k/4k from 10 tps to 20 tps. ### 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. -->
hanbitmyths
pushed a commit
that referenced
this pull request
May 18, 2024
### Description This PR adds support for adding GroupQueryAttention (GQA) in models that are running on CPU. ### Motivation and Context Previously, the LLaMA scripts supported creating models that have GQA for CUDA only. With the recently added support for [GQA on CPU](#20299), models where `num_attention_heads != num_key_value_heads` can now use the GQA op and [run much faster on CPU](#20598).
poweiw
pushed a commit
to poweiw/onnxruntime
that referenced
this pull request
Jun 25, 2024
### Description <!-- Describe your changes. --> optimize the GQA implementation on CPU. Mainly optimization are: 1. compute attention on real total sequence length instead of maximum sequence length in case past/present share same buffer 2. remove the mask 3. remove the transpose after attention x value It improve the phi3 model https://github.com/microsoft/onnxruntime-genai/blob/main/examples/python/phi3-qa.py with max sequence length 2k/4k from 10 tps to 20 tps. ### 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. -->
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
optimize the GQA implementation on CPU. Mainly optimization are:
It improve the phi3 model https://github.com/microsoft/onnxruntime-genai/blob/main/examples/python/phi3-qa.py with max sequence length 2k/4k from 10 tps to 20 tps.
Motivation and Context