(feat): refactor agentic rl design, async training, add distill/dpo/lora feature, etc. - #111
Merged
Conversation
…gpqa-diamond reward worker.
|
|
PanAndy
changed the title
…d by async agentic pipeline.
PanAndy
force-pushed
the
sync/sync_to_github_ROLL_0730
branch
from
July 30, 2025 10:55
a497696 to
63f9fab
Compare
Collaborator
Author
Collaborator
Author
|
#25 |
PanAndy
force-pushed
the
sync/sync_to_github_ROLL_0730
branch
from
July 31, 2025 03:18
63f9fab to
87007f5
Compare
PanAndy
force-pushed
the
sync/sync_to_github_ROLL_0730
branch
from
July 31, 2025 03:21
87007f5 to
5d48a39
Compare
Collaborator
Author
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
9 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
(docs): add QA doc.
(feat): refactor agentic rl design.
(feat): Group Sequence Policy.
(fix) fix the issue with saving critic checkpoints.
(fix): fix wrong step-off steps, add special case for async_generate_…
(fix): improve exception reporting in RolloutScheduler.
(chore): webshop change actor train to megatron.
(feat): add Distill pipeline.
(fix): fix concurrent bug when abort request in ActorWorker introduce…
(fix): fix dead loop when multiple coroutine are waken up in GroupQue…
(feat): vlm multi domain rlvr pipeline.
(feat): add DPO pipeline.
(feat): set torch load weight_only.
(feat): resume ckpt from download model path.
(test): test model_update_pipeline_multi_group.
(feat): add multi model update.
(feat): refine mcore_adapter.
(feat): dump rvlr rollout.
(feat): async training agentic pipeline.
(feat): add the newest math test dataset and gpqa-diamond, and a new …
(fix): fix code test environment.
feat: add CLAUD.md for claud code.
(feat): automap concurrency issue.
(fix): Qwen3 Dense FP8 Compat Fixes.
(feat): support lora training.