Skip to content

[ExecuTorch][WebGPU] Migrate quantized_linear to make_compute_pipeline#20870

Open
JCNTH wants to merge 3 commits into
gh/JCNTH/45/basefrom
gh/JCNTH/45/head
Open

[ExecuTorch][WebGPU] Migrate quantized_linear to make_compute_pipeline#20870
JCNTH wants to merge 3 commits into
gh/JCNTH/45/basefrom
gh/JCNTH/45/head

Conversation

@JCNTH

@JCNTH JCNTH commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

Stack from ghstack (oldest at bottom):

Route the q4gsw quantized_linear op through utils::make_compute_pipeline (layout:"auto"), completing the migration of every pipeline-building op to the shared helper. Preserved exactly: the 3-way shader_src routing (bicol GEMV for M==1 / shmem GEMM for large K,N / tiled GEMM otherwise), the fixed_wgconstant_count (0/1) toggle for the wg_size override (only the tiled GEMM carries the override; GEMV and shmem are fixed 64 lanes), the dummy t_bias binding (real-or-scratch at binding 4), the resize hook, own_uniform_buffer, dispatch counts, and all validation.

Precondition verified before migrating: all 3 selectable q4gsw shaders (q4gsw_linear_coop4_bicol, q4gsw_linear_gemm_shmem, q4gsw_linear tiled) statically reference t_bias at binding 4 under the if (params.has_bias != 0u) guard, so layout:"auto" retains binding 4 — the 6-entry bind group (out + in/weight/scales/bias + uniform) matches.
@exported-using-ghexport

Differential Revision: D110836663

Differential Revision: D110836663

[ghstack-poisoned]
@pytorch-bot

pytorch-bot Bot commented Jul 10, 2026

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20870

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

❌ 57 New Failures, 2 Unrelated Failures, 7 Unclassified Failures

As of commit 263849f with merge base c2b273e (image):

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:

  • pull / unittest / windows / windows-job (gh) (matched win rule in flaky-rules.json)
    Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under 'C:\actions-runner\_work\executorch\executorch\test-infra\.github\actions\teardown-windows'. Did you forget to run actions/checkout before running your local action?
  • pull / unittest-editable / windows / windows-job (gh) (matched win rule in flaky-rules.json)
    Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under 'C:\actions-runner\_work\executorch\executorch\test-infra\.github\actions\teardown-windows'. Did you forget to run actions/checkout before running your local action?

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

@github-actions

Copy link
Copy Markdown

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.

[ghstack-poisoned]
[ghstack-poisoned]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. meta-exported

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants