CUDA: fix __builtin_assume for CUDA < 11.2 #2669
Closed
Conversation
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
cebtenzzre
reviewed
Aug 19, 2023
|
It does compile now, and seems to be working too. BTW, this patch is also needed: ggml-org/whisper.cpp#1018 (comment) And because the older nvcc doesn't support the --forward-unknown-to-host-compiler option:
|
ggerganov
approved these changes
Sep 14, 2023
|
Closed in favor of #3132 |
vieenrose
added a commit
to vieenrose/whisper.cpp-Jetson-nano
that referenced
this pull request
Dec 18, 2023
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Outdated suggestions cannot be applied.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.
Reportedly there are compilation issues on old CUDA versions due to
__builtin_assume, see #2458 (comment) . This PR attempts to fix the issue by defining a dummy implementation for old CUDA versions. I don't have old CUDA versions installed on any of my old machines, so I did not test that the dummy implementation actually fixes the compilation issues (but the code seemed to work correctly with CUDA 12 when using the dummy implementation). @whoreson please confirm that this fixes the compilation issue for you.