[tinker] 7/n towards Kimi K2.6: apply client LoRA config before config validation - #2029
Merged
erictang000 merged 1 commit intoAug 19, 2026
Conversation
…g validation create_lora_training_client requests were rejected whenever the backend config enables trainer.policy.model.fake_int4_qat: the client's LoRA rank/alpha were assigned onto the config *after* from_cli_overrides, so TrainerConfig.__post_init__ validated fake_int4_qat against the default lora.rank=0 and raised "fake_int4_qat requires LoRA" even for LoRA clients. Inject rank/alpha into the override dict (client wins over backend_config, matching the previous post-assignment semantics) so validation sees the real rank. Co-authored-by: Cursor <cursoragent@cursor.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request modifies skyrl/backends/skyrl_train_backend.py to apply LoRA rank and alpha configurations to the user_overrides dictionary before instantiating SkyRLTrainConfig via from_cli_overrides. This ensures that post-initialization validation checks, such as verifying that fake_int4_qat.enabled requires lora.rank > 0, are executed correctly. There are no review comments, so I have no feedback to provide.
erictang000
approved these changes
Aug 19, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Injects the client-requested LoRA rank/alpha into the override dict passed to
from_cli_overridesinstead of assigning them onto the config afterwards (client wins over backend_config, matching the previous post-assignment semantics).Why
create_lora_training_clientrequests were rejected whenever the backend config enablestrainer.policy.model.fake_int4_qat:TrainerConfig.__post_init__validatedfake_int4_qatagainst the defaultlora.rank=0and raised "fake_int4_qat requires LoRA" even for LoRA clients, because the client's rank/alpha arrived after validation.Part of the Kimi K2.x series (follow-up to #1862). Independent of the other PRs in the series.
Made with Cursor