Skip to content

[executorch][native] Judge activation-quantized engines against an int8-activation golden - #24537

Open
pytorchbot wants to merge 1 commit into
gh/digantdesai/188/origfrom
gh/digantdesai/189/orig
Open

pytorchbot wants to merge 1 commit into
gh/digantdesai/188/origfrom
gh/digantdesai/189/orig

Conversation

@pytorchbot

Copy link
Copy Markdown
Collaborator

This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #24362 by @digantdesai
^ 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/digantdesai/189/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/digantdesai/189/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/digantdesai/188/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/digantdesai/189/orig

@diff-train-skip-merge

…t8-activation golden

Pull Request resolved: #24362

With activation quantization allowed, ggml's weight-only linears no longer compute what `golden` describes. Weight-only packages now carry `golden-int8_act`, eager with int8 per-token dynamic activations, which `sample_test_main` judges against under `--allow_activation_quant_for_weight_only`. The flag is a `HostOptions` field that Vulkan rejects; new `ggml_sample_test_act_quant` targets and the `native_ggml_sample_test_act_quant` ctest set it.

Authored with Claude Code.

@bypass-github-export-checks
@bypass-github-pytorch-ci-checks
@bypass-github-executorch-ci-checks
ghstack-source-id: 463657755
@exported-using-ghexport

Differential Revision: [D128254888](https://our.internmc.facebook.com/intern/diff/D128254888/)
@pytorch-bot

pytorch-bot Bot commented Nov 3, 2026 •

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24537

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

❌ 3 New Failures, 3 Pending, 1 Unrelated Failure

As of commit 34cac2a with merge base 0f8e096 (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following job failed but was likely due to flakiness present on trunk:

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

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Nov 3, 2026

This branch was previously deployed

1 inactive deployment
cadence — 34cac2ab Deployed Nov 3, 2026 by pytorchbot via hifi-op-test / hifi4 #36368
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.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants