feat(hslm): progressive quantization — FP32 warmup → ternary anneal#566
Merged
Conversation
- Add src/b2t/progressive_quantization.zig - 4-stage schedule: fp32_warmup → fp16_transition → ternary_anneal → full_ternary - Progressive threshold decay: init_threshold → final_threshold - quantizeWeights: stage-dependent weight modification - Temperature-controlled ternary transition - Quantization loss weight increases with schedule progress - 5 tests: stage progression, fp32 preserves precision, full ternary output, progress tracking, loss weight monotonicity Closes #321
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Progressive quantization schedule: FP32 warmup → FP16 transition → ternary anneal → full ternary.
New file
src/b2t/progressive_quantization.zig— 191 LOCSchedule
Tests (5)
Closes #321