Extend ConstrainedGenerationSession with rollback, jump-forward, and direct bitmask fill - #131
Merged
stikves merged 4 commits intoJul 31, 2026
Conversation
stikves
requested review from
alejandro-isaza,
carinapeng,
kevchengcodes and
tjia1818
July 31, 2026 15:32
stikves
force-pushed
the
sukru/constrained-session-extensions
branch
from
July 31, 2026 15:52
b504d3d to
c94798c
Compare
…direct bitmask fill - rollback(_:) — unwind grammar state by N tokens (budget: 64) - findJumpForwardString() — peek at deterministic continuations - fillBitmask(into:) → BitmaskResult — write bitmask directly into a caller-provided pointer (e.g. GPU-visible MTLBuffer), avoiding array allocation per token - BitmaskResult enum: .terminated, .unconstrained, .constrained - C bridge additions: XGrammarRollback, XGrammarFindJumpForwardString, XGrammarFillNextTokenBitmask Part 1 of 4 for GPU-based constrained sampling (apple#114).
stikves
force-pushed
the
sukru/constrained-session-extensions
branch
from
July 31, 2026 15:55
c94798c to
9b507bc
Compare
carinapeng
reviewed
Jul 31, 2026
carinapeng
reviewed
Jul 31, 2026
carinapeng
approved these changes
Jul 31, 2026
stikves
force-pushed
the
sukru/constrained-session-extensions
branch
from
July 31, 2026 18:22
6695020 to
ad7c77a
Compare
stikves
force-pushed
the
sukru/constrained-session-extensions
branch
from
July 31, 2026 18:24
ad7c77a to
4d8189a
Compare
stikves
force-pushed
the
sukru/constrained-session-extensions
branch
2 times, most recently
from
July 31, 2026 19:29
acc7fd6 to
977ad20
Compare
2 tasks
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
New methods for constrained generation:
Part 1 of 4 for GPU-based constrained sampling (#114).