Don't detect local GPU if $DS_IGNORE_CUDA_DETECTION is set#7896
Open
Flamefire wants to merge 2 commits intodeepspeedai:masterfrom
Open
Don't detect local GPU if $DS_IGNORE_CUDA_DETECTION is set#7896Flamefire wants to merge 2 commits intodeepspeedai:masterfrom
$DS_IGNORE_CUDA_DETECTION is set#7896Flamefire wants to merge 2 commits intodeepspeedai:masterfrom
Conversation
Make this consistent over all OPs: For cross-compilation we should not check the local GPU version.
sfc-gh-truwase
approved these changes
Mar 12, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Make this consistent over all OPs:
For cross-compilation we should not check the local GPU version.
This is also important when having multiple different GPUs in the system, so checking only GPU 0 could be wrong.
It looks like checks for the version of CUDA should be moved out of this and checks for compute capability vs CUDA version moved to
filter_ccsinstead.CUDAOpBuilder.is_compatiblecould callcompute_capability_argsto see if the CCs after filtering turn up empty.