Expose DeepSWE controls in distributed workers. - #2162
Merged
Conversation
copybara-service
Bot
requested review from
abheesht17,
hgao327,
jiangyangmu,
lc5211,
s-noghabi,
sizhit2,
tianshub and
wang2yn84
as code owners
September 9, 2026 07:53
copybara-service
Bot
force-pushed
the
test_978370082
branch
6 times, most recently
from
September 10, 2026 21:16
d294bdc to
12add65
Compare
Support --enable_thinking for rollout nodes, and configure prompt-level mini-batch gradient accumulation and AdamW optimizer parameters in trainer nodes. PiperOrigin-RevId: 979416686
copybara-service
Bot
force-pushed
the
test_978370082
branch
from
September 10, 2026 22:02
12add65 to
9d36029
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Expose DeepSWE controls in distributed workers.
Support --enable_thinking for rollout nodes, and configure prompt-level mini-batch gradient accumulation and AdamW optimizer parameters in trainer nodes.