Repository navigation
Conversation
…r (FromPixels with replicate padding, ToPixels with crop and alpha copy; bit-identical to the removed PixelOps converters on 160 random cases x 4 formats x both layouts; the NCHW variants now also split rows across threads). CPU / Vulkan e2e at parity with main. Needs the next Sdcb.SimdOnnx preview Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…s pixels; drop an unused local (review) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
sdcb
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Sdcb.SimdOnnx.Imaging.ImageTensor(FromPixelswith replicate padding,ToPixelswith crop and alpha copy). The fourPixelOpsconverters are removed.tools/ab-gcdr.ps1, two interleaved rounds, ±3% noise); memory unchanged.Sdcb.SimdOnnx 0.1.0-preview.5(ProGet test feed), which also brings faster per-shape compiles, GPU const packing outside the GC heap and the Metal op-set additions.🤖 Generated with Claude Code