[digantdesai]

Stack from ghstack (oldest at bottom):

• [executorch][native] Record dynamic-shape linears as chained bundled samples #24405
• [executorch][native] Run the ggml CPU act_quant sample test in CI #24373
• [executorch][vulkan] Round f16 image stores to nearest even #24372
• [executorch][native-vk] Note the int4 weight-only N % 4 and rank-4 linear gaps #24371
• [executorch][vulkan] Fix dq8ca q4gsw weight sums stride when N % 8 is 1 to 4 #24370
• [executorch][vulkan] Accept 1-D activations in 8da4w linear #24369
• [executorch][native] Cover negative, rounded and subnormal GGUF super-block scales in the op samples #24368
• [executorch][native] Decode quantized weights in float32 for precise samples #24367
• [executorch][native] Add GGUF q4_k and q6_k packages to the op samples #24366
• [executorch][native] Add FACTO-drawn linear cases to the op samples #24365
• [executorch][native] Suggest rounding to nearest when engines narrow values #24364
• [executorch][native-ggml] Compute cuBLAS GEMMs in f32 in the CUDA sample tests #24363
• [executorch][native] Judge activation-quantized engines against an int8-activation golden #24362
• [executorch][native-ggml] Reject weight-only quantized linears unless activation quant is allowed #24361
• [executorch][native] Run engines on bundled op samples with gtest #24360
• [executorch][native] Judge engine outputs against golden and precise samples #24359
• [executorch][native] Pin eager kernels when generating op samples #24358
• -> [executorch][native] Record op packages with bundled golden and precise samples #24357
• [executorch][native] Split engine host factories out of the PTN runners #24356
• [executorch][test-suite] Feed the Linear tests inputs with the model's 67 input features #24355

Engines need op-level reference data that doesn't depend on any engine or device. op_samples writes one .ptn per op and quantization scheme, bundling golden (eager) and precise (float64, weights dequantized, activations unquantized) samples over the same inputs. Linear is the first op. Schemes are float, int4wo g32/g128 and 8da4w g32/g128, each with f32, f16 and bf16 methods; int8 weight-only is left out because no native engine runs it. Linear cases are the backend test suite's models, reused through a stand-in runner, plus decode, prefill, large-K, bias-free leading-batch, outlier-channel and zero-row cases. With CMake, the native_op_samples target writes them; it is not in ALL, so a plain build never needs torch.

Ops and schemes are independent axes. An op is an Op in ops(), a function returning Cases plus the dtypes to record them in; a scheme is a Scheme in schemes() that decides which cases it fits, quantizes a model and decodes its weights. generate records every op under every scheme, one spawned process per package, and writes no package when a scheme fits none of an op's cases. cases.py holds the case type and the backend test suite adapter, schemes.py the quantization, and record.py the packaging, which knows neither torchao nor any op.

Authored with Claude Code.

@bypass-github-export-checks
@bypass-github-pytorch-ci-checks
@bypass-github-executorch-ci-checks
@exported-using-ghexport

Differential Revision: D128254877

Differential Revision: D128254877

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24357

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure, 4 Unclassified Failures

As of commit 4b89ceb with merge base 0f8e096 ():

NEW FAILURE - The following job has failed:

• pull / nxp-mcuxpresso-test / linux-job (gh)
  undefined reference to SYS_INFO_PrintAll'`

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:

• Build Windows CUDA Wheels / bundle-cuda-windows-wheel-e2e-13.2 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found
• Build Windows CUDA Wheels / pytorch/executorch / build-wheel-py3_11-cuda13_2 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  ##[error]Process completed with exit code -2147483644.
• Build Windows CUDA Wheels / pytorch/executorch / upload / upload-wheel-py3_11-cuda13_2 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found
• Build Windows CUDA Wheels / test-cuda-windows-wheel-e2e-13.2 / windows-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[SS-JIA]

Review automatically exported from Phabricator review in Meta.