[ExecuTorch][WebGPU] Coalesce SDPA AV V-cache reads along contiguous head-dim#20508
Open
pytorchbot wants to merge 1 commit into
Open
[ExecuTorch][WebGPU] Coalesce SDPA AV V-cache reads along contiguous head-dim#20508pytorchbot wants to merge 1 commit into
pytorchbot wants to merge 1 commit into
Conversation
…head-dim Pull Request resolved: #20459 **~19% faster SDPA attention-output (AV) stage** — 393→317 µs on llama3 prefill (Chrome Canary / M4 Pro). **Problem**: V-cache reads load 4 strided context rows × 1 head-dim lane, missing coalescing. **Solution**: Flip access pattern to read 4 contiguous head-dim lanes per context row: - **Before**: `load_v_vec4(d, kvh, c4)` → 4 strided rows, `dot()` along D - **After**: `load_v_d4(c, kvh, d0)` → 4 contiguous D-lanes (16-byte texel), scalar broadcast **Implementation**: - Reindex `load_v` helper to read contiguous head-dim - Replace `dot(A, V)` with `acc += A[c] * V_vec4(d0:d0+3)` - Mirrors Vulkan `load_v_cache_d4` coalescing pattern **Constraints**: - No KV-cache layout change (still `[C, Hkv, D]`) - Output numerically identical (FP-reassociated, max abs diff 1.43e-6 vs torch) ghstack-source-id: 396792504 @exported-using-ghexport Differential Revision: [D109339276](https://our.internmc.facebook.com/intern/diff/D109339276/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20508
Note: Links to docs will display an error until the docs builds have been completed. ❗ 2 Active SEVsThere are 2 currently active SEVs. If your PR is affected, please view them below:
❌ 3 New Failures, 1 Unrelated FailureAs of commit eb9073c with merge base e03f777 ( NEW FAILURES - The following jobs have failed:
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. |
meta-cla
Bot
added
the
CLA Signed
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: #20459 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/54/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/54/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/49/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/54/orig
@diff-train-skip-merge