Repository navigation
Handle empty products in mul! without BLAS, and treat β = 0 as a strong zero - #100
Merged
Merged
Conversation
…ng zero Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Codecov Report✅ All modified and coverable lines are covered by tests.
🚀 New features to boost your workflow:
|
kshyatt
approved these changes
Nov 3, 2026
This was referenced Nov 3, 2026
Merged
lkdvos
referenced
this pull request
Nov 3, 2026
Co-authored-by: Claude Opus 5.5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes two edge cases of
mul!forStridedViews, found by the new backend test suite of TensorOperations.jl.mul!now only scalesCbyβ, and returns before the BLAS dispatch. Previously these went to BLAS, which fails for GPU arrays (cuBLAS does not accept the empty matrices).β: ifα == 0or the inner dimension is empty,__mul!scaledCwithrmul!(C, β), so aβ = 0keptNaNs that were already inC, e.g. from uninitialized memory. A zeroβnow overwritesCwith zeros, as BLAS does. Both cases use a small_scale!helper.Tests
blasmultests.jl:Cfilled withNaN, andβ = 0withαzero or one, with an empty inner dimension, foridentityandconjviews.gpu.jl: an empty inner dimension.blasmultests.jlandgpu.jlpass locally onJLArrayandCuArray(3475 tests).🤖 Generated with Claude Code