feat: Add fused attention output + RMSNorm support for GPT-OSS #148
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
Integrate AITER's new fused_attn_output_rmsnorm kernel into GPT-OSS model. Changes: - Add ATOM_ENABLE_FUSED_ATTN_OUTPUT_RMSNORM env variable (default: disabled) - Update TransformerBlock to use fused kernel when enabled - Supports x_pad_to_multiple for MoE compatibility Usage: export ATOM_ENABLE_FUSED_ATTN_OUTPUT_RMSNORM=1 Requires: AITER with fused_attn_output_rmsnorm kernel
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Outdated suggestions cannot be applied.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
Integrate AITER's new \ used_attn_output_rmsnorm\ kernel into GPT-OSS model.
Changes
Usage
\\�ash
export ATOM_ENABLE_FUSED_ATTN_OUTPUT_RMSNORM=1
\\
Dependencies
Requires: AITER PR ROCm/aiter#1863 merged first
Performance Benefits