feat: VLM primitives — vision ops, NN layers, encoder models#96
Merged
Conversation
Core ops (rmlx-core): - interpolate: bilinear/bicubic Metal kernels, align_corners support - pixel_normalize: per-channel (pixel-mean)/std, ImageNet defaults - pool2d: avg/max pooling with configurable kernel/stride/padding NN layers (rmlx-nn): - PatchEmbedding: Conv2d + reshape for image→patch sequence - VisionPositionalEmbedding: learned + grid2D - VisionTransformerBlock: pre-norm bidirectional attention - MultiModalProjector: Linear or MLP (fc1→GELU→fc2) - Attention::forward_no_cache() for vision (no RoPE, no mask, no KV cache) Vision encoder models: - ViT-Base/16 (768h, 12L), ViT-Large/14 (1024h, 24L) - SigLIP SO400M/14 (1152h, 27L, no class token) - CLIP ViT-L/14-336 (1024h, 24L, QuickGELU) - HF weight name mapping for vision encoders Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Test plan
cargo check --workspacepassescargo fmt --all --checkpassescargo clippy --workspace --all-targetspasses (fixed large_enum_variant warning)🤖 Generated with Claude Code