UPSTREAM PR #18436: CUDA: Blackwell features for non-native builds #731
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
loci-dev
temporarily deployed
to
PROD__AL_DEMO
GitHub Actions
Inactive
|
Explore the complete analysis inside the Version Insights Perfect! I've generated a summary report for your project. Here are the key highlights: Summary Report for llama.cpp PR #731Performance Impact: ✅ MINIMAL (Safe to Merge) The analysis compared two versions of the auroralabs-loci/llama.cpp repository and found:
Conclusion: This pull request is performance-neutral and safe to merge from a performance perspective. The changes introduced do not cause any measurable performance regressions or improvements. The report analyzed:
|
loci-dev
force-pushed
the
main
branch
2 times, most recently
from
f2e8c7f to
b3f45e1
Compare
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Outdated suggestions cannot be applied.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.
Mirrored from ggml-org/llama.cpp#18436
This PR adds architectures to enable the recent Blackwell-specific MXFP4 optimizations for non-native builds. The problem with
120f-virtualwhich we were using in the initial PR is that it doesn't match some regex that CMake was using to validate CUDA architectures. But the same regex seems to be compatible with120a-realand121a-realso I would suggest that we for now simply build those since there is no other hardware to cover. Newer CMake versions come with a bugfix for the regex so presumably this will be less problematic for us to handle in the future. @CISC is there a way to run the Windows CUDA release CI without merging a PR?