Repository navigation
Keep policy versions unique when a trainer resumes behind the store's releases - #328
Merged
Merged
Conversation
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 2, 2026 17:31
4dfe1a1 to
d564b00
Compare
michaellchung
force-pushed
the
resume-version-account
branch
from
November 2, 2026 17:31
9fce8ce to
d770015
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 2, 2026 17:42
d564b00 to
ec4c078
Compare
michaellchung
force-pushed
the
resume-version-account
branch
from
November 2, 2026 17:42
d770015 to
e8a6c81
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 2, 2026 18:30
ec4c078 to
fa54896
Compare
michaellchung
force-pushed
the
resume-version-account
branch
from
November 2, 2026 18:30
e8a6c81 to
2aed9e1
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 2, 2026 18:42
fa54896 to
91226de
Compare
michaellchung
force-pushed
the
resume-version-account
branch
from
November 2, 2026 18:42
2aed9e1 to
1caf025
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 2, 2026 19:27
91226de to
7ed7c17
Compare
michaellchung
force-pushed
the
resume-version-account
branch
from
November 2, 2026 19:27
1caf025 to
00c334d
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 2, 2026 19:58
7ed7c17 to
c60a94d
Compare
michaellchung
force-pushed
the
resume-version-account
branch
2 times, most recently
from
November 2, 2026 20:09
bf73f0c to
dc0309e
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 2, 2026 20:09
c60a94d to
933f436
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 3, 2026 02:05
933f436 to
7ec663b
Compare
michaellchung
force-pushed
the
resume-version-account
branch
from
November 3, 2026 02:05
dc0309e to
a9212e7
Compare
michaellchung
force-pushed
the
background-release-mfu
branch
from
November 3, 2026 03:29
7ec663b to
6ef9f6e
Compare
michaellchung
force-pushed
the
resume-version-account
branch
from
November 3, 2026 03:29
a9212e7 to
f424f86
Compare
… releases - bridges: a buffer trainer whose round cut is behind the store's newest release continues the version account above it (resume_at, behind_round_cuts; LocalOnlySync.start). - Miles single trainer: on relaunch the publisher continues above the store's releases (_resume_single_trainer, ReleasingPublisher resumed_base) instead of reusing a version already released. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
michaellchung
force-pushed
the
resume-version-account
branch
from
November 3, 2026 04:09
f424f86 to
38eee6a
Compare
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
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.
Summary
bridges: a buffer trainer whose round cut is behind the store's newest release continues the version account above it (resume_atwithbehind_round_cuts;LocalOnlySync.start), so a resumed run never re-publishes a version that already exists._resume_single_trainer,ReleasingPublisherresumed_base) instead of reusing a version already released.Behavior changes
LATESTin the release store no longer moves back to the resumed checkpoint's version. The first release of the relaunched trainer gets the next version above the store's newest release, so versions stay unique and monotonic; samplers that followLATESTnever see it regress.Test plan
pytest tests/test_rl_sampler_island.py tests/test_rl_verl_buffer_trainer.pyplus the earlier stacked suites: 290 passed.scripts/precommit_check.pyon the changed files: no errors.Stacked on #327.
🤖 Generated with Claude Code