Allow frame stacking with text context#15585
Merged
rfejgin merged 1 commit intoNVIDIA-NeMo:mainfrom Apr 7, 2026
Merged
Conversation
But still error out if the context length would be too short to fit commonly used text contexts. Signed-off-by: Fejgin, Roy <rfejgin@nvidia.com>
paarthneekhara
approved these changes
Apr 7, 2026
Collaborator
paarthneekhara
left a comment
paarthneekhara
left a comment
There was a problem hiding this comment.
LGTM.
Not for this PR, but we should probably take in a parameter specifying max text context length so that we accidentally dont give longer than ~105 tokens for text context. We can use that value for verification (instead of 5 seconds at 21FPS)
blisc
approved these changes
Apr 7, 2026
Collaborator
Author
I agree. I will create a JIRA issue to track that. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This change removes the restriction on combining frame stacking and text context.
We still need to be careful that the context's sequence length after stacking is long enough to accommodate the text context, which does not get stacked. So a check was added to verify that the context sequence length is the at least as long as what we'd get with the standard 5-second context and no stacking, a configuration that is known to (almost always) fit existing text contexts.