ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON#18413
Merged
am17an merged 1 commit intoggml-org:masterfrom Dec 28, 2025
Merged
ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON#18413am17an merged 1 commit intoggml-org:masterfrom
am17an merged 1 commit intoggml-org:masterfrom
Conversation
github-actions
bot
added
Nvidia GPU
JohannesGaessler
approved these changes
Dec 27, 2025
Contributor
JohannesGaessler
left a comment
JohannesGaessler
left a comment
There was a problem hiding this comment.
This should be correct since CMAKE_CUDA_ARCHITECTURES is a user input and CMAKE_CUDA_ARCHITECTURES_NATIVE seems to be a variable that CMake sets itself internally.
am17an
added a commit
to am17an/llama.cpp
that referenced
this pull request
Dec 28, 2025
…VE=ON (ggml-org#18413)" This reverts commit 4fd59e8.
am17an
added a commit
that referenced
this pull request
Dec 28, 2025
This was referenced Dec 28, 2025
blime4
referenced
this pull request
in blime4/llama.cpp
Feb 5, 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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixed compilation error when building with GGML_NATIVE=ON and CUDA Toolkit but without a GPU (e.g.
docker build) whereCMAKE_CUDA_ARCHITECTURES_NATIVEwill beNo CUDA Devices found., causing nvcc errorUnsupported gpu architecture 'compute_No CUDA Devices found.'.Also if
CMAKE_CUDA_ARCHITECTURESis explicitly set by the user, maybe it's better to use it even whenGGML_NATIVE=ON. Which is also consistent with the behavior before #18361.Additionally moves the logging of
CMAKE_CUDA_ARCHITECTURESafter the replacement.Possibly related to #18398.