[ExecuTorch][WebGPU] Add q8ta_conv2d_dw op (int8 depthwise conv)#21201
Open
JCNTH wants to merge 1 commit into
Open
[ExecuTorch][WebGPU] Add q8ta_conv2d_dw op (int8 depthwise conv)#21201JCNTH wants to merge 1 commit into
JCNTH wants to merge 1 commit into
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21201
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: ❌ 44 New Failures, 3 Unrelated FailuresAs of commit c6ed46b with merge base 266e0dc ( NEW FAILURES - The following jobs have failed:
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 was referenced Jul 22, 2026
This was referenced Jul 22, 2026
This PR needs a
|
meta-cla
Bot
added
the
CLA Signed
psiddh
approved these changes
Jul 23, 2026
psiddh
left a comment
psiddh
left a comment
Contributor
There was a problem hiding this comment.
Approving full WebGPU stack
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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):
Problem: The WebGPU delegate has no quantized depthwise convolution. A depthwise
nn.Conv2d(groups == channels) through XNNPACK static PT2E lowers to a delegatedquantize_per_tensor -> q8ta_conv2d_dw -> dequantize_per_tensorsubgraph; the quantize/dequantize are the landed C0 ops, soq8ta_conv2d_dwis the one missing piece to run a quantized depthwise conv end-to-end.Solution: Port
et_vk.q8ta_conv2d_dw(int8 activation x int8 per-channel weight -> int8). Depthwise means groups == C == OC: each output channel c convolves only input channel c with its own Kh x Kw filter. Per output element:acc = Σ_{kh,kw} (x_int8[n,c,ih,iw] - input_zero_point) * weight_int8[kh,kw,c]withih = oh*stride_h - pad_h + kh*dil_h,iw = ow*stride_w - pad_w + kw*dil_w(out-of-bounds taps skipped = zero padding); dequantizeacc * input_scale * weight_scales[c] + bias, requantizeclamp(round(v * inv_output_scale) + output_zero_point, -128, 127), packed 4 int8 per word. Mirrors Vulkanq8ta_conv2d_dw(Q8taConv2dDW.cpp+q8ta_conv2d_dw.glsl) and the landedconv1d_dwwindowing.Implementation:
Q8taConv2dDw.cppregistersq8ta_conv2d_dw.default,out = args.back(), one thread per output word = 4 consecutiveW_outpositions of a fixed(n, c, oh)(W_out % 4 == 0for output word alignment), 2D dispatch fold to lift the 65535 cap. Reads full conv geometry (stride/padding/dilationint-lists,groups) and guardsgroups == C == OC,[N,C,H_in,W_in]/[Kh,Kw,OC]/[N,C,H_out,W_out]ranks, int8 dtypes, andactivation == "none"(all fail-loud).Q8taConvDwParamsis an 80-byte (16-aligned) uniform.Constraints / divergences from the Vulkan reference (numerically equivalent, golden-verified): (1) the
weight_sumsarg is unused — the input zero-point correction is folded per-element (Σ(x-zp)·w == Σx·w - zp·Σw), so it matches Vulkan'sweight_sumscompensation exactly, including at zero-padded taps. (2) weight arrives raw[Kh,Kw,OC]int8 (the AOT pattern's depthwise reshapepermute(2,3,1,0); the WebGPU prepack is a passthrough), not Vulkan's int8x4-block 4W4C texture layout.activationscoped to"none"(the XNNPACK-static default; relu-fused is fail-loud, a follow-up).Differential Revision: D112257645