[data.llm] Deserialize arrays for sampling_params #52631
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
Signed-off-by: Arthur <atte.book@gmail.com>
Contributor
kouroshHakha
left a comment
kouroshHakha
left a comment
There was a problem hiding this comment.
Thanks a ton. One comment while I triggered ci
kouroshHakha
changed the title
ArthurBook
force-pushed
the
fix-llm-sampling-params-stop-token-ids
branch
2 times, most recently
from
2cd88cd to
00e493e
Compare
Signed-off-by: Arthur <atte.book@gmail.com>
ArthurBook
force-pushed
the
fix-llm-sampling-params-stop-token-ids
branch
from
00e493e to
74849c1
Compare
kouroshHakha
approved these changes
Apr 27, 2025
Contributor
|
Thanks @ArthurBook ! |
iamjustinhsu
pushed a commit
that referenced
this pull request
May 3, 2025
Signed-off-by: Arthur <atte.book@gmail.com> Signed-off-by: jhsu <jhsu@anyscale.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
Why are these changes needed?
This solves the issue described in #52630
Some vllm sampling params such as
stop_token_idsare lists and hence get converted to np.arrays when sent from one process to another in ray data. This causes a deserialization error in the vLLM engine since it expects a list, not a np.array.Related issue number
Closes #52630
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.