[ExecuTorch][WebGPU] Add optimized SDPA op#20851
Open
JCNTH wants to merge 3 commits into
Open
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20851
Note: Links to docs will display an error until the docs builds have been completed. ❌ 128 New Failures, 3 Unrelated Failures, 7 Unclassified FailuresAs of commit 1323ba1 with merge base c2b273e ( NEW FAILURES - The following jobs have failed:
UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
meta-cla
Bot
added
the
CLA Signed
This was referenced Jul 10, 2026
[ExecuTorch][WebGPU] Add relu op (shared unary handler; sigmoid adopts make_compute_pipeline)
#20863
Open
This was referenced Jul 10, 2026
This was referenced Jul 16, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack from ghstack (oldest at bottom):
Adds a non-causal fused scaled-dot-product-attention kernel to the WebGPU backend, enabling the attention blocks of vision encoders (Florence-2 DaViT / SigLIP, SAM2) and non-causal cross-attention (BART) to run end-to-end on GPU.
Problem — the delegate had no kernel for
et_vk.sdpa.default, the plain non-causal attentionsoftmax(q @ kᵀ * scale + attn_mask) @ vthat the et_vk source transform plugs into every vision-encoder attention block. Without it the attention layers broke the graph. This is distinct from the causal KV-cachesdpa_with_kv_cache: no cache, an optional additive mask, and it must handle asymmetric sequence lengths (S_q != S_kv, e.g. a Hiera pooled query or cross-attention).Solution
et_vk_sdpa_implchains three compute dispatches over[B, H, S, D](DSHB) row-major tensors —et_vk_sdpa_qk.wgslcomputes the scaledQ·Kᵀscores plus an optional additive mask, the reusedsdpa_softmax.wgsldoes the row-wise softmax, andet_vk_sdpa_av.wgslcomputessoftmax · Vinto the output.Implementation
et_vk_sdpa_qk.wgsl): one GPU thread per(b, h, s)row of the[B, H, S_q, S_kv]attention-weight buffer;q/kare bound asarray<vec4<f32>>overD, and the thread loops overc(key positions) andd4(D/4) accumulatingdot(q4, k4), then multiplies byscaleand addsmask[...]whenhas_mask. Row countB*H*S_qstays well under the 1D dispatch limit for any ViT.sdpa_softmax.wgsl(one workgroup per row, hardcoded@workgroup_size(64,1,1)) dispatched on a near-square 2D workgroup grid past the 65535 ceiling; the shader recovers the flat row index from@builtin(num_workgroups), so no override constant is needed.et_vk_sdpa_av.wgsl): one thread per(b, h, s, d4)computing avec4<f32>of four output elements;v/outare bound asarray<vec4<f32>>overDand the thread contracts overcscalar (S_kvis not guaranteed% 4 == 0), accumulatingsm[...] * v4.attn,softmax, eachB*H*S_q*S_kv) are allocated viagraph.create_scratch_buffer;scaledefaults to1/sqrt(D)when the arg isNoneor takes theDoublevalue; the three uniforms are compact structs (QkParams/AvParams32 bytes,SoftmaxParams16 bytes).utils::make_compute_pipeline,utils::make_uniform,utils::check_vec4_aligned(guardsD % 4 == 0),utils::clamp_workgroup_size+utils::compute_1d_workgroup_count(QK / AV grids),utils::compute_2d_workgroup_count(softmax grid), andutils::make_optional_binding(a 4-byte dummy satisfies the mask binding when absent; the shader never reads it underhas_mask == 0).backends/vulkan/runtime/graph/ops/impl/SDPA.cppSDPAMode::FUSED(general non-cache SDPA,[B, H, S, D]DSHB layout, optional additiveattn_mask, optionalscale, unpadded fp32 attention weights).Constraints — fp32 only (bails on
q/outbyte mismatch); non-causal (causality is expressed as a baked additive mask input, not a code path);D % 4 == 0for the vec4 QK/AV kernels (every model in scope usesD=64or128);qrank ≥ 3;k.dims == v.dims,q/k/vshareHandDand all leading batch dims, andout.dims == q.dims; asymmetricS_q != S_kvis supported (reduces bit-identically to self-attention when equal); a supplied mask must be[B, H, S_q, S_kv]fp32.Co-authored-with: Claude Code.
@exported-using-ghexport
Differential Revision: D110836679
Differential Revision: D110836679