Cuda kernel - #53
Closed
MathisWellmann wants to merge 1 commit into
Closed
Conversation
MathisWellmann
force-pushed
the
cuda-kernel
branch
from
July 28, 2026 00:20
6159346 to
8f5e8d8
Compare
MathisWellmann
marked this pull request as ready for review
July 28, 2026 00:20
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Include example
cuda-softmaxto showcasesymbiontbeing able to let LLMs implement and optimize CUDA kernels.An LLM writes CUDA kernels, the host compiles them with NVRTC, checks them
against a CPU oracle, times them on the GPU, and feeds the achieved memory
throughput back into the next round. The best kernel is hot-swapped in; the
rest stay registered as revisions.