kernel-builder: add CUDA capability detection for tvm-ffi builds#357
Merged
kernel-builder: add CUDA capability detection for tvm-ffi builds#357
Conversation
Make the CMake build to detect the CUDA capability of the GPU by default. This speeds up builds when developing, since we only need to compile for a single capability. Kernels still get built for the full of capabilities when doing a regular kernel build, since it passes `BUILD_ALL_SUPPORTED_ARCHS=ON`.
sayakpaul
previously approved these changes
Mar 16, 2026
| @@ -36,7 +36,7 @@ endif() | |||
| set(KERNEL_REVISION "{{ revision }}" CACHE STRING "Kernel revision, must be unique") | |||
| set(OPS_NAME "_{{python_name}}_${BACKEND}_{{ revision }}") | |||
|
|
|||
| option(BUILD_ALL_SUPPORTED_ARCHS "Build all supported architectures" on) | |||
| option(BUILD_ALL_SUPPORTED_ARCHS "Build all supported architectures" off) | |||
Member
Author
There was a problem hiding this comment.
This mirrors the Torch version. It was set to on for tvm-ffi because the detection is not implemented yet. We set it to on in the Nix builder, so that official builds get the full range of capabilities:
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 the CMake build to detect the CUDA capability of the GPU by default. This speeds up builds when developing, since we only need to compile for a single capability. Kernels still get built for the full of capabilities when doing a regular kernel build, since it passes
BUILD_ALL_SUPPORTED_ARCHS=ON.Fixes #354.