[metal] Add fused RMS_NORM + MUL + SWIGLU for Qwen3Next #16143
+74
−14
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Outdated suggestions cannot be applied.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.
This PR adds a new fused operator in the Metal backend to support
Qwen3NextRMSNormGated
from Qwen3-Next models:kernel_rms_norm_fuse_impl
withF == 4
: fusesrms_norm + mul + swiglu_split
into a single kernel.Qwen3NextRMSNormGated
inmodeling_qwen3_next.py
.SWIGLU_SPLIT
as a fusible tail op.test_rms_norm_mul_add
test class to cover the new fusion pattern.test-backend-ops
with full parameter coverage (broadcast, eps, multi_add).Tested on Apple M4 Pro. All tests pass.
Related to #15940