docs: document fit_mode="fit_with_cache" in the README - #354
Merged
Conversation
Adds a KV Cache section next to Thinking Mode: what the flag is for, the fit-once-predict-many shape via `model_id_`, and the thinking-mode incompatibility. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The cache is built during fit(), not warmed by the first predict. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
brendan-priorlabs
approved these changes
Aug 11, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Georg written description: just docs
Claude generated description
fit_modeandapi_modeare the headline additions of 0.4.x and neither appears in the README. This adds a KV Cache section next to Thinking Mode, matching its shape: one-line purpose, a snippet, themodel_id_fit-once-predict-many pattern, and three notes.Kept to the caller's view — what the flag does for them, not how it is served.
Two claims I checked against prod rather than assuming: predictions match the uncached path, and a reused
model_id_returns the original class labels without settingclasses_(an earlier draft said otherwise).api_modeis still undocumented; separate PR.