Skip to content

Add RotaryEmbeddings(23) - CUDA#25178

Merged
titaiwangms merged 10 commits intomicrosoft:mainfrom
titaiwangms:titaiwang/support_rotary_embed_onnx_cuda
Jul 7, 2025
Merged

Add RotaryEmbeddings(23) - CUDA#25178
titaiwangms merged 10 commits intomicrosoft:mainfrom
titaiwangms:titaiwang/support_rotary_embed_onnx_cuda

Conversation

@titaiwangms
Copy link
Contributor

@titaiwangms titaiwangms commented Jun 25, 2025

Follow up #24980
Fix #24556

Add ONNX RotaryEmbedding(23) following https://github.com/onnx/onnx/blob/main/docs/Operators.md#RotaryEmbedding. The PR uses contrib op RotaryEmbedding implementation under the hood.

The main difference between this op and the contrib op is that the position_ids in ONNX RotaryEmbedding is optional. When it's not provided, cos_cache and sin_cache should be 3d.

@titaiwangms titaiwangms marked this pull request as ready for review June 26, 2025 20:45
@titaiwangms
Copy link
Contributor Author

@tianleiwu PTAL

tianleiwu
tianleiwu previously approved these changes Jul 3, 2025
@titaiwangms titaiwangms merged commit 15e75af into microsoft:main Jul 7, 2025
87 of 90 checks passed
@titaiwangms
Copy link
Contributor Author

Merged to catch feature complete deadline. Let me know if there ae follow-ups needed.

daijh pushed a commit to daijh/onnxruntime that referenced this pull request Jul 10, 2025
Follow up microsoft#24980
Fix microsoft#24556

Add ONNX RotaryEmbedding(23) following
https://github.com/onnx/onnx/blob/main/docs/Operators.md#RotaryEmbedding.
The PR uses contrib op RotaryEmbedding implementation under the hood.

The main difference between this op and the contrib op is that the
position_ids in ONNX RotaryEmbedding is optional. When it's not
provided, cos_cache and sin_cache should be 3d.
qti-yuduo pushed a commit to CodeLinaro/onnxruntime that referenced this pull request Aug 8, 2025
Follow up microsoft#24980
Fix microsoft#24556

Add ONNX RotaryEmbedding(23) following
https://github.com/onnx/onnx/blob/main/docs/Operators.md#RotaryEmbedding.
The PR uses contrib op RotaryEmbedding implementation under the hood.

The main difference between this op and the contrib op is that the
position_ids in ONNX RotaryEmbedding is optional. When it's not
provided, cos_cache and sin_cache should be 3d.
sanketkaleoss pushed a commit to sanketkaleoss/onnxruntime that referenced this pull request Aug 11, 2025
Follow up microsoft#24980
Fix microsoft#24556

Add ONNX RotaryEmbedding(23) following
https://github.com/onnx/onnx/blob/main/docs/Operators.md#RotaryEmbedding.
The PR uses contrib op RotaryEmbedding implementation under the hood.

The main difference between this op and the contrib op is that the
position_ids in ONNX RotaryEmbedding is optional. When it's not
provided, cos_cache and sin_cache should be 3d.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Feature Request] Implement RotaryEmbedding-23

4 participants