Skip to content

fix multimodal data and max_token arguments when using vllm tokenizer (text mode)#4

Merged
wangshangsam merged 7 commits intoCentML:mlperf-inf-mm-q3vl-v6.0from
soodoshll:fix-mm-input
Feb 2, 2026
Merged

fix multimodal data and max_token arguments when using vllm tokenizer (text mode)#4
wangshangsam merged 7 commits intoCentML:mlperf-inf-mm-q3vl-v6.0from
soodoshll:fix-mm-input

Conversation

@soodoshll
Copy link

Overview:

Details:

Where should the reviewer start?

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

  • closes GitHub issue: #xxx

soodoshll and others added 6 commits February 1, 2026 21:55
Signed-off-by: Qidong Su <soodoshll@gmail.com>
@github-actions
Copy link

github-actions bot commented Feb 2, 2026

👋 Hi soodoshll! Thank you for contributing to CentML/dynamo.

Just a reminder: The NVIDIA Test Github Validation CI runs an essential subset of the testing framework to quickly catch errors.Your PR reviewers may elect to test the changes comprehensively before approving your changes.

🚀

@wangshangsam wangshangsam merged commit 876e6d6 into CentML:mlperf-inf-mm-q3vl-v6.0 Feb 2, 2026
6 of 10 checks passed
zhandaz pushed a commit that referenced this pull request Feb 4, 2026
… (text mode) (#4)

* fix

* ups

Signed-off-by: Qidong Su <soodoshll@gmail.com>

* upd

* update

* fix

* upd

* fix

---------

Signed-off-by: Qidong Su <soodoshll@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants