Skip to content

[ET-VK] Support setting cache_data_path at run time #11382

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 4, 2025

Conversation

pytorchbot
Copy link
Collaborator

This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #11350 by @jorgep31415
^ 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/jorgep31415/136/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/jorgep31415/136/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/jorgep31415/135/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/jorgep31415/136/orig
@diff-train-skip-merge

…nes call

Pull Request resolved: #11345

We target the QC Adreno driver implementation of Vulkan. The Vulkan API does not enforce how QC actually uses the cache. As the plural naming of `vkCreateComputePipelines` suggests, we observed that the `createInfoCount`, `pCreateInfos` and `pPipelines` arguments above allow construction of multiple compute pipelines in one invocation. We refactor ET-VK to accumulate metadata necessary for pipeline construction and invoke vkCreateComputePipelines only once. QC's implementation maximizes the cache if we create the same number of compute pipelines in fewer invocations of vkCreateComputePipelines. This decreases model load for a sample model from 1.7s to 200ms.
ghstack-source-id: 288170368

Differential Revision: [D75763660](https://our.internmc.facebook.com/intern/diff/D75763660/)
Pull Request resolved: #11350
TSIA

ghstack-source-id: 288183826
@exported-using-ghexport

Differential Revision: [D75918105](https://our.internmc.facebook.com/intern/diff/D75918105/)
@pytorchbot pytorchbot requested a review from SS-JIA as a code owner June 4, 2025 22:44
Copy link

pytorch-bot bot commented Jun 4, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11382

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

⏳ No Failures, 32 Pending

As of commit 767b781 with merge base af0a246 (image):
💚 Looks good so far! There are no failures yet. 💚

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

@facebook-github-bot facebook-github-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 Jun 4, 2025
Base automatically changed from gh/jorgep31415/135/orig to main June 4, 2025 23:04
@SS-JIA SS-JIA merged commit 6415c15 into main Jun 4, 2025
95 checks passed
@SS-JIA SS-JIA deleted the gh/jorgep31415/136/orig branch June 4, 2025 23:16
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.

4 participants