feat(sc): abort stale in-flight rollouts early under over_sampling - #3263
Open
RayenTian wants to merge 5 commits into
Open
feat(sc): abort stale in-flight rollouts early under over_sampling#3263RayenTian wants to merge 5 commits into
RayenTian wants to merge 5 commits into
Conversation
25 tasks
RayenTian
force-pushed
the
ruit/sc-entrypoint-gate
branch
3 times, most recently
from
August 1, 2026 06:17
5aaedbb to
cc02515
Compare
Contributor
Author
|
/ok to test cc02515 |
RayenTian
commented
Aug 1, 2026
RayenTian
marked this pull request as ready for review
August 1, 2026 07:05
RayenTian
force-pushed
the
ruit/sc-entrypoint-gate
branch
from
August 1, 2026 13:58
cc02515 to
728de3f
Compare
Contributor
Author
|
/ok to test 728de3f |
Contributor
Author
|
/ok to test 2019c54 |
yuki-97
reviewed
Aug 3, 2026
yuki-97
left a comment
Contributor
There was a problem hiding this comment.
thanks for supporting this, changes overall LGTM. left some comments and one q for nemo-gym path.
| ) # Default 15 minutes | ||
|
|
||
| # Propagate cancellation to the Ray worker and its vLLM request. | ||
| try: |
Contributor
There was a problem hiding this comment.
curious have you tested whether nemo-gym path works? since the changes in vLLM all seem to be native async path.
RayenTian
force-pushed
the
ruit/sc-entrypoint-gate
branch
from
August 4, 2026 05:48
2019c54 to
e5ed92b
Compare
Signed-off-by: ruit <ruit@nvidia.com>
Signed-off-by: ruit <ruit@nvidia.com>
Signed-off-by: ruit <ruit@nvidia.com>
Signed-off-by: ruit <ruit@nvidia.com>
Signed-off-by: ruit <ruit@nvidia.com>
RayenTian
force-pushed
the
ruit/sc-entrypoint-gate
branch
from
August 4, 2026 06:17
0416763 to
43baf36
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
train/evicted_stale_prompt_groups) and aborted stale in-flight groups (train/aborted_stale_inflight_groups).Tests
Recipe: examples/configs/recipes/llm/performance/grpo-llama3.1-8b-instruct-2n8g-async-1off.yaml
disable kv cache recompute
enable kv cache recompute