[Native WebGPU EP] Add packedQKV and do_rotary attribute support to GroupQueryAttention operator #23386
+189
−52
Conversation
This file contains 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
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Comment on lines
142
to
145
| shader.MainFunctionBody() << " if (n + local_id.y < uniforms.kv_sequence_length) {\n" | ||
| " tileK[idx] = key[kOffset + (n + local_id.y) * uniforms.K + w + local_id.x];\n" | ||
| " tileK[idx] = " << (is_packed_qkv_ ? "q" : "key") << "[kOffset + (n + local_id.y) * uniforms.K + w + local_id.x];\n" | ||
| " }\n"; | ||
| } |
There was a problem hiding this comment.
Suggested change
| shader.MainFunctionBody() << " if (n + local_id.y < uniforms.kv_sequence_length) {\n" | |
| " tileK[idx] = key[kOffset + (n + local_id.y) * uniforms.K + w + local_id.x];\n" | |
| " tileK[idx] = " << (is_packed_qkv_ ? "q" : "key") << "[kOffset + (n + local_id.y) * uniforms.K + w + local_id.x];\n" | |
| " }\n"; | |
| } | |
| shader.MainFunctionBody() << " if (n + local_id.y < uniforms.kv_sequence_length) {\n" | |
| " tileK[idx] = " | |
| << (is_packed_qkv_ ? "q" : "key") << "[kOffset + (n + local_id.y) * uniforms.K + w + local_id.x];\n" | |
| " }\n"; | |
| } |
Comment on lines
172
to
177
| return ApplyAttention(&qRotary, &kRotary, &vBNSH, nullptr, past_key, past_value, output, present_key, | ||
| present_value, parameters, context, seqlens_k); | ||
| } else { | ||
| return ApplyAttention(&qBNSH, &kBNSH, &vBNSH, nullptr, past_key, past_value, output, present_key, | ||
| present_value, parameters, context, seqlens_k); | ||
| } |
There was a problem hiding this comment.
Suggested change
| return ApplyAttention(&qRotary, &kRotary, &vBNSH, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } else { | |
| return ApplyAttention(&qBNSH, &kBNSH, &vBNSH, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } | |
| return ApplyAttention(&qRotary, &kRotary, &vBNSH, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } else { | |
| return ApplyAttention(&qBNSH, &kBNSH, &vBNSH, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } |
Comment on lines
188
to
193
| return ApplyAttention(&qRotary, nullptr, nullptr, nullptr, past_key, past_value, output, present_key, | ||
| present_value, parameters, context, seqlens_k); | ||
| } else { | ||
| return ApplyAttention(&qBNSH, nullptr, nullptr, nullptr, past_key, past_value, output, present_key, | ||
| present_value, parameters, context, seqlens_k); | ||
| } |
There was a problem hiding this comment.
Suggested change
| return ApplyAttention(&qRotary, nullptr, nullptr, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } else { | |
| return ApplyAttention(&qBNSH, nullptr, nullptr, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } | |
| return ApplyAttention(&qRotary, nullptr, nullptr, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } else { | |
| return ApplyAttention(&qBNSH, nullptr, nullptr, nullptr, past_key, past_value, output, present_key, | |
| present_value, parameters, context, seqlens_k); | |
| } |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
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.
Description
Add Packed QKV inputs and do_rotary attribute to GQA.
Motivation and Context
Packed QKV inputs and do_rotary attribute are required for certain models.