-
Notifications
You must be signed in to change notification settings - Fork 1
Setup prompt-processsing and token-generation testing in text generation tasks #229
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
titaiwangms
wants to merge
13
commits into
sdpython:main
from
titaiwangms:titaiwang/fix_modelbuilder_discrepancy
Closed
Setup prompt-processsing and token-generation testing in text generation tasks #229
titaiwangms
wants to merge
13
commits into
sdpython:main
from
titaiwangms:titaiwang/fix_modelbuilder_discrepancy
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
titaiwangms
commented
Sep 23, 2025
onnx_diagnostic/torch_export_patches/patches/patch_transformers.py
Outdated
Show resolved
Hide resolved
Collaborator
Author
Owner
|
CI is not running. I wonder why so I can't tell if the tests are passing. Let me create a temporary PR. |
Owner
|
CI is running. |
sdpython
reviewed
Sep 24, 2025
onnx_diagnostic/torch_export_patches/patches/patch_transformers.py
Outdated
Show resolved
Hide resolved
Collaborator
Author
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Outdated suggestions cannot be applied.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.
Previous to this PR, in text-generation task, we are exporting and testing LLMs with multi-turn conversation, where the model runs "prompt processing" --> [for loop for "token generation"] --> using the for loop output for prompt processing again, and the whole run is restricted to have
batch_size=1in GQA contrib op.In this PR, we export LLMs with token generation setting, and test the model with both token generation and prompt processing scenario.
Cited @kunal-vaishnavi
These are the general shapes:
Prompt processing (aka prefill):
Token generation (aka decode):