Add metal-std-version field and kernels-test-utils package#331
Draft
robtaylor wants to merge 3 commits intohuggingface:mainfrom
Draft
Add metal-std-version field and kernels-test-utils package#331robtaylor wants to merge 3 commits intohuggingface:mainfrom
robtaylor wants to merge 3 commits intohuggingface:mainfrom
Conversation
Allow per-kernel Metal standard version configuration via build.toml, following the pattern of cuda-flags, hip-flags, and sycl-flags. The default remains metal4.0 (upstream's current value). Kernels that need broader macOS compatibility can set metal-std-version = "metal3.1" (macOS 14+) or "metal3.2" (macOS 15+). AIR versions are forward- compatible, so metal3.1 kernels run on Metal 4 hardware. Changes: - Add metal_std_version field to Kernel::Metal in config structs (v2, v3, mod) - Pass field through Jinja template context to generated CMake - Accept METAL_STD_VERSION in metal_kernel_component() and propagate to compile_metal_shaders() via parent scope - Default to metal4.0 in compile-metal.cmake when not specified - Set metal-std-version = "metal3.1" in relu-metal-cpp example for broad macOS 14+ compatibility Co-developed-by: Claude Code v2.1.58 (claude-opus-4-6)
Create a shared test utilities package that consolidates duplicated device detection, tolerance tables, and allclose helpers across all kernel repos. The package is automatically available in all kernel dev/test shells via the default pythonCheckInputs. Modules: - device: get_device(), get_available_devices(), skip_if_no_gpu() - tolerances: DEFAULT_TOLERANCES dict, get_tolerances(dtype) - allclose: fp8_allclose() with MPS float64 workaround Wired into nix overlay and set as default pythonCheckInputs in genKernelFlakeOutputs so downstream repos get it automatically. Updated template test to use kernels_test_utils imports. Co-developed-by: Claude Code v2.1.58 (claude-opus-4-6)
Co-developed-by: Claude Code v2.1.58 (claude-opus-4-6)
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.
Summary
metal-std-version: Allow per-kernel Metal standard version configuration via
build.toml, following the pattern ofcuda-flags,hip-flags, andsycl-flags. The default remainsmetal4.0. Kernels needing broader macOS compatibility can setmetal-std-version = "metal3.1"(macOS 14+) or"metal3.2"(macOS 15+). AIR versions are forward-compatible, sometal3.1kernels run on Metal 4 hardware.kernels-test-utils: Shared Python test utilities package that consolidates duplicated device detection, tolerance tables, and allclose helpers across all kernel repos. Auto-injected into all kernel dev/test shells via the default
pythonCheckInputsingenKernelFlakeOutputs. Downstream repos (rotary-embedding, fused-rms-norm, dequant-int4, dequant-gguf) already use it.Changes
metal-std-version
metal_std_versionfield toKernel::Metalin config structs (v2, v3, mod)METAL_STD_VERSIONinmetal_kernel_component()and propagate tocompile_metal_shaders()via parent scopemetal4.0incompile-metal.cmakewhen not specifiedmetal-std-version = "metal3.1"in relu-metal-cpp examplekernels-test-utils
kernels-test-utils/package:device.py,tolerances.py,allclose.pynix/pkgs/python-modules/kernels-test-utils/nix/overlay.nixpythonCheckInputsinflake.nixauto-injects into all downstream shellskernels_test_utilsimportsTest plan
nix build .#relu-metal-cpppasses withmetal-std-version = "metal3.1"nix develop ./builder/examples/relu-metal-cpp→python -c "from kernels_test_utils import get_device; print(get_device())"worksCo-developed-by: Claude Code v2.1.58 (claude-opus-4-6)