chore: make src the server package root#117
Merged
Merged
Conversation
ShubyM
force-pushed
the
feat/package-structure
branch
17 times, most recently
from
b9419dd to
5af835f
Compare
ShubyM
force-pushed
the
feat/package-structure
branch
from
90e508f to
d896832
Compare
ShubyM
force-pushed
the
feat/package-structure
branch
from
d896832 to
d77c33f
Compare
droot
approved these changes
Jun 10, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR fixes #115, which makes src the actual python root package and splits the code under src into 3 sections: training, server and snapshot agent. I also added a set of local tests we can run as we start refactoring and introducing more pieces into open-rl to verify core behavior.
make testruns the fast unit tests, andmake test e2eruns one of the local GPU training flows. The tiny-* scenarios are intentionally small overfit/smoke tests: they use a minimal prompt or rollout setup so we can quickly check that LoRA SFT, FFT SFT, and LoRA RL can actually run and update the model without committing to a full benchmark. The heavier scenarios are lora-textsql, fft-gsm8k, and fft-gsm8k-x2, where the last one runs two FFT jobs against the snapshot-agent path.