fix: make simd module public (was pub(crate)) Consumers (bgz-tensor, thinking-engine) need ndarray::simd::bf16_to_f32_batch and other polyfill exports. Was incorrectly restricted to pub(crate). https://claude.ai/code/session_01ChLvBfpJS8dQhHxRD4pYNp#82
Merged
Conversation
1. Intrinsics nightly-only → asm!() works on stable 2. Tile config must be 64-byte aligned → #[repr(C, align(64))] 3. rbx is LLVM-reserved → use __cpuid_count() 4. OS must enable via XSETBV → check XCR0 bits 17+18 5. TILEZERO/TILERELEASE need raw bytes → encodings documented 6. Tile config field layout → byte offsets documented 7. Wrong config = SEGFAULT → start minimal, expand 8. is_x86_feature_detected nightly → use __cpuid_count https://claude.ai/code/session_01ChLvBfpJS8dQhHxRD4pYNp
…osine table
Complete pipeline for ThinkingEngine brain construction:
1. Normalize f32 centroids to unit vectors
2. Quantize [-1,1] → u8 [0,255]
3. Tiered VNNI/AMX dot product (build_distance_table_vnni)
4. Map i32 dots → u8 cosine [0=opposite, 128=orthogonal, 255=identical]
Separated: build_cosine_table() for the ThinkingEngine (takes f32, returns u8)
build_distance_table_vnni() for raw u8 dot products (existing)
https://claude.ai/code/session_01ChLvBfpJS8dQhHxRD4pYNp
Consumers (bgz-tensor, thinking-engine) need ndarray::simd::bf16_to_f32_batch and other polyfill exports. Was incorrectly restricted to pub(crate). https://claude.ai/code/session_01ChLvBfpJS8dQhHxRD4pYNp
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.