-
Notifications
You must be signed in to change notification settings - Fork 166
fix: fix error padding #87
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
Merged
Merged
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
parthchadha
reviewed
Mar 26, 2025
79e8957 to
886db53
Compare
658a33b to
3657084
Compare
4 tasks
SahilJain314
reviewed
Apr 1, 2025
cbaa4f0 to
0d3f20f
Compare
cf5097d to
eb6d9c1
Compare
eb6d9c1 to
c67634c
Compare
a7b6c50 to
c9d52cf
Compare
parthchadha
previously approved these changes
Apr 3, 2025
terrykong
reviewed
Apr 3, 2025
terrykong
reviewed
Apr 3, 2025
|
Could you also update the guidance here? IIUC, the guidance now is something like: |
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
c9d52cf to
b9642bf
Compare
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
b9642bf to
9e6a116
Compare
sure! updated. |
terrykong
approved these changes
Apr 4, 2025
parthchadha
approved these changes
Apr 7, 2025
parthchadha
pushed a commit
that referenced
this pull request
Apr 11, 2025
Signed-off-by: Yuki Huang <yukih@nvidia.com> Co-authored-by: Terry Kong <terrycurtiskong@gmail.com> Signed-off-by: Parth Chadha <pchadha@nvidia.com>
KiddoZhu
pushed a commit
that referenced
this pull request
May 6, 2025
Signed-off-by: Yuki Huang <yukih@nvidia.com> Co-authored-by: Terry Kong <terrycurtiskong@gmail.com>
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.
What does this PR do ?
Now generate by vllm will contain 0 instead of correct pad_token_id.
This PR is to fix this by:
Pass correct pad_value_dict to
BatchedDataDict.from_batcheswhen combining generated results, then output_ids will be pad by pad_token_id instead of 0.This PR also organize the tokenizer and corresponding config settings into
get_tokenizerandconfigure_generation_config, and calling the two functions at beginning to get the correctly set up tokenizer and update config.Issues
List issues that this PR closes (syntax):
Usage
# Add a code snippet demonstrating how to use thisBefore your PR is "Ready for review"
Pre checks:
Additional Information