[ExecuTorch][WebGPU] Add et_vk.apply_rotary_emb (interleaved RoPE) + ValueList multi-output#20426
Merged
JulianCloudNTH merged 4 commits intoJun 22, 2026
Merged
Conversation
…ValueList multi-output Pull Request resolved: #20264 Adds the WebGPU backend handler for `et_vk.apply_rotary_emb.default` (interleaved Llama rotary positional embedding) plus the `ValueList` graph-value support its multi-output signature requires. The op rotates the query and key tensors by a shared `freqs_cos`/`freqs_sin` pair and is composed of two dispatches of one WGSL kernel: each thread handles one (even, odd) element pair of a head row (`out[2i] = x[2i]*cos - x[2i+1]*sin`, `out[2i+1] = x[2i]*sin + x[2i+1]*cos`), one dispatch writing `xq_out` and one writing `xk_out`, mirroring the Vulkan `apply_rotary_emb` reference (buffer-only, fp32, the interleaved `.default` variant). Each dispatch owns a distinct compute pipeline (the graph destructor releases per dispatch, so a shared handle would double-free); the workgroup size is a `wg_size` pipeline-override constant clamped to the device limit, both 1D dispatch counts go through `WebGPUUtils::compute_1d_workgroup_count` and are validated before any GPU-object allocation, and the embedded WGSL header is generated by `gen_wgsl_headers.py`. The two outputs (`xq_out`, `xk_out`) are serialized by the Vulkan exporter as a single `ValueList` graph value, which the runtime did not previously model. This adds the `ValueType::ValueList` value kind, a `value_lists_` table populated during `build()`, and a `get_value_list` accessor the handler uses to resolve the output ids. While in that code path it also closes a latent gap: a constant tensor whose `constant_id` is set but whose constants table is missing or out of range now throws (fail-loud) rather than silently leaving the buffer uninitialized. ghstack-source-id: 395549282 @exported-using-ghexport Differential Revision: [D108428756](https://our.internmc.facebook.com/intern/diff/D108428756/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20426
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
JulianCloudNTH
approved these changes
Jun 22, 2026
…ve golden) Pull Request resolved: #20290 Splits the `et_vk.apply_rotary_emb` tests into their own diff (op below, tests above), matching the `sdpa`/`update_cache`/`linear_q4gsw` convention, and brings them to the same rigor: a multi-shape config sweep run on-device (prefill + decode) and a library dual-oracle at both shapes. ghstack-source-id: 395549287 @exported-using-ghexport Differential Revision: [D108668384](https://our.internmc.facebook.com/intern/diff/D108668384/)
…E2E weight loading Pull Request resolved: #20265 Adds the WebGPU backend handler for `et_vk.prepack.default`, the node the VulkanPartitioner wraps around every constant feeding a delegated op so the constant is materialized into its dedicated GPU buffer before inference. For the WebGPU backend's buffer-flat/fp32 model, prepack is an identity layout (same dims, dtype, and bytes), so the handler runs no compute shader: it validates that `src` and `out` match (dims, `elem_size`, `nbytes`, non-null buffers; every check throws fail-loud) and records a one-time `src`->`out` buffer-to-buffer copy via the new `WebGPUGraph::add_prepack_copy`. The recorded copies run once in a new `build()` Phase 4 (after the op-dispatch chain is recorded), mirroring the Vulkan delegate's separate `prepack()` init phase (distinct from per-inference `execute()`). Ordering is guaranteed by the WebGPU queue -- the prepack submit precedes the first `execute()` submit on the same queue, so the copied data is visible without an explicit device poll (Dawn has no `wgpuDevicePoll`, and the backend relies on queue ordering plus the output-map wait elsewhere). `src.elem_size` is the `WebGPUTensor` field added by the embedding op lower in this stack, so prepack stacks above it. ghstack-source-id: 395549289 @exported-using-ghexport Differential Revision: [D108428754](https://our.internmc.facebook.com/intern/diff/D108428754/)
Pull Request resolved: #20292 Test suite for the `et_vk.prepack` constant-materialization op, split into its own diff (op below, tests above) per the per-op test-split convention. The prepack op is how a serialized constant becomes a GPU tensor: the constant arrives as a CPU-side reference (sizes + a pointer into the .pte bytes), and the prepack node is the sole materialization — one CPU->GPU transfer straight into the consumer's buffer. The model `M(x) = x + w` (w a constant) routes `w` through a prepack node, so the delegate must run the materialization for the output to equal `x + w` rather than `x + 0`. ghstack-source-id: 395555139 @exported-using-ghexport Differential Revision: [D108678631](https://our.internmc.facebook.com/intern/diff/D108678631/)
JulianCloudNTH
merged commit 1c65102
into
gh/JulianCloudNTH/28/orig
144 of 151 checks passed
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: #20264 by @JulianCloudNTH
^ 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/JulianCloudNTH/26/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/26/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/28/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/26/orig
@diff-train-skip-merge