[ExecuTorch][WebGPU] Op-tests for linear_qcs4w#21212
Open
JCNTH wants to merge 1 commit into
Open
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21212
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: ❌ 46 New Failures, 3 Unrelated FailuresAs of commit 64fff8c 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 new
et_vk.linear_qcs4wop needs golden coverage — and, being a quantized op reachable only through a specific quantizer, a test that actually produces the op and validates the fake-quant numerics.Solution:
make_qcs4w_linear_moduleruns a plainnn.Linearthrough theVulkanQuantizerweight-only 4-bit path (get_symmetric_quantization_config(is_dynamic=False, weight_bits=4)-> prepare_pt2e -> calibrate -> convert_pt2e), and the op-testmodule_factoryreturns the CONVERTED module, so the WebGPU output is goldened against the converted eager (fp32 per-channel fake-quant reference). This exercises the int4 unpack + per-channel dequant end-to-end.bias=Falsekeeps the golden focused on qcs4w (a Linear bias lowers to a separateaten.add).Implementation:
cases.pyregisterslinear_qcs4wwithbasic(4x32x16),gemv(M=1 decode shape),k64(2x64x8),n32(3x32x32) — all with K even (2 nibbles/byte) andN*ceil(K/2) % 4 == 0(u32-packed weight);test_linear_qcs4w.pyholds the module + a delegation smoke test assertinget_vk.linear_qcs4wis absorbed into the VulkanBackend delegate.Differential Revision: D112257668