Conversation
Extract the identical scalar iterator logic (max-token clamp, next-token selection) shared by CoreAISequentialEngine and CoreAISequentialVLMEngine into a SequentialIterator namespace both call, and tidy the VLM engine: drop the addressed re-use TODO, dedup the post-warmup/reset state-clear into clearGenerationState(), and refresh the class docs to describe the now-shared decode machinery. Behavior-preserving; each engine keeps its own generation control flow.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follows #249 (B1+B2). Third step of the VLM/text sequential-engine consolidation.
Changes
CoreAISequentialEngineandCoreAISequentialVLMEngine) into aSequentialIteratornamespace both call. Each engine keeps its ownnext()loop: the text engine's batched forced-continuation PPL path and prefix cache, the VLM engine's image prefill.clearGenerationState(), update the class doc.No behavior change.
Tests
New
SequentialIteratorTests(clamp, next-token). Existing suites pass underswift test --disable-sandbox.Validation
Bit-exact vs the pre-refactor baseline: text greedy 128/128, forced-continuation PPL exact; VLM greedy 115/115 and 400/400.
Notes
Not a full generic iterator: the text batched-PPL path stays in place rather than being merged. C1+C2 (factory-based VLM construction, CLI-fork removal) follow in a stacked PR.