Fixes for Windows #2206
Merged
Fixes for Windows #2206
Conversation
This file contains 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
Codecov ReportAttention:
Additional details and impacted files@@ Coverage Diff @@
## master #2206 +/- ##
==========================================
- Coverage 72.97% 72.95% -0.02%
==========================================
Files 159 159
Lines 14656 14648 -8
==========================================
- Hits 10695 10687 -8
Misses 3961 3961 ☔ View full report in Codecov by Sentry. |
LiorSinai
added a commit
to LiorSinai/TransformersLite.jl
that referenced
this pull request
Dec 23, 2023
This can be reverted once JuliaGPU/CUDA.jl#2206 is fully merged
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Outdated suggestions cannot be applied.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.
Among other things, reverts #2109 (cc @utkarsh530). Turns out that broadcast's (ab)use of
Refboxes for scalar arguments is a problem: Ephemeral objects like that get freed quickly, leading to illegal memory accesses on the GPU. We could root all arguments, but that would make launching kernels more expensive. I'm inclined to just not support a use case like that, at least for now. If people care greatly about this, please comment in #267. For now, this should fix FluxML/Zygote.jl#1473.