[ET-VK] Add fused HuggingFace RoPE operator (apply_rotary_emb_hf)#18599
Merged
[ET-VK] Add fused HuggingFace RoPE operator (apply_rotary_emb_hf)#18599
Conversation
Pull Request resolved: #18592 Add a fused rotary positional embedding operator for the HuggingFace RoPE convention used by Qwen3, Phi-4-mini, and other HF-based models. The existing `et_vk.apply_rotary_emb` only matches the stock Meta/Llama RoPE pattern (interleaved pairs via reshape+unbind+stack+flatten). HF models use a different convention (split-half via slice+neg+cat), causing Qwen3's RoPE to decompose into ~560 GPU dispatches per decode step instead of 16 fused dispatches (~1,295 µs/decode, 7% of total). This commit adds `et_vk.apply_rotary_emb_hf` with: - Pattern matching: `HfRotaryEmbeddingPattern` in `patterns/rope_hf.py` using SubgraphMatcher to detect the HF RoPE graph and replace with fused op. Supports both full rotation (freqs_dim == head_dim) and partial rotation (freqs_dim < head_dim, e.g. Phi-4-mini with partial_rotary_factor=0.75) by registering two pattern variants in get_hf_rope_graphs(). - GLSL shader: `rotary_embedding_hf.glsl` which pairs elements at distance D/2 (half-apart) instead of adjacent pairs, computing half_dim from the metadata UBO for dynamic shape support - C++ dispatch: `add_rotary_embedding_hf_node` with corrected assertion (head_dim == freqs_dim, not freqs_dim*2) since HF freqs are full-dim - Custom op registration in both xplat and fbcode - Op tests covering multiple configurations and dynamic prefill→decode resize Also adds a convert_phi4_mini_weights binary target to the phi_4_mini TARGETS file to enable converting HF checkpoint weights to Meta format. Authored with Claude. ghstack-source-id: 359963407 @exported-using-ghexport Differential Revision: [D98741178](https://our.internmc.facebook.com/intern/diff/D98741178/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18599
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 2 Unrelated FailuresAs of commit 48db8ce with merge base d7cc5d7 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This PR needs a
|
SS-JIA
approved these changes
Mar 31, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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 was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #18592 by @SS-JIA
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/514/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/514/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/514/orig
Differential Revision: D98741178
@diff-train-skip-merge