feat: Add fused attention output + residual + RMSNorm kernel #1863
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
Add a new fused Triton kernel that combines: - Attention output - Residual connection (optional) - RMSNorm - Output padding (optional, for MoE) Performance benefits: - Reduces kernel launch overhead (3 kernels -> 1) - Saves memory bandwidth (no intermediate writes) - ~1.2-1.4x speedup in attention-heavy workloads New files: - aiter/ops/triton/_triton_kernels/fusions/fused_attn_output_rmsnorm.py - aiter/ops/triton/fusions/fused_attn_output_rmsnorm.py - aiter/ops/triton/configs/FUSED-ATTN_OUTPUT-RMSNORM.json - op_tests/triton_tests/fusions/test_fused_attn_output_rmsnorm.py
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
| import os | ||
|
|
||
| if not hasattr(_get_config, "_config_dict"): | ||
| dev = arch_info.get_arch() |
Contributor
| start = time.time() | ||
| for _ in range(100): | ||
| x = attn_output + residual | ||
| output_unfused = rmsnorm_reference(x, weight) |
Contributor
Member
|
@ChuanLi1101 Please fix the Black and Ruff code style issues first |
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Outdated suggestions cannot be applied.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.
Summary
Add a new fused Triton kernel that combines:
Performance Benefits
Files Changed
Usage
\\python
from aiter.ops.triton.fusions import fused_attn_output_rmsnorm
Basic usage
output = fused_attn_output_rmsnorm(attn_output, weight)
With residual and padding
output, residual = fused_attn_output_rmsnorm(
attn_output, weight,
residual=x,
x_pad_to_multiple=256
)
\\
Testing