[ET-VK][BE] Move all ops to use DynamicDispatchNode
#13098
Closed
Conversation
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
## Changes Update (almost) all operators use `DynamicDispatchNode` instead of `DispatchNode`. ## Context `DynamicDispatchNode` was introduced in order to provide a way for operators to adjust 1. Which compute shader to dispatch 2. What global work group size to use 3. What local work group size to use Based on the current input and output shapes. This is useful for making sure that the most optimal compute shader is used for the current tensor sizes, and minimizing the number of inactive shader invocations. Differential Revision: [D79564595](https://our.internmc.facebook.com/intern/diff/D79564595/) [ghstack-poisoned]
This was referenced Aug 4, 2025
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13098
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: ❌ 3 New Failures, 1 Unrelated FailureAs of commit 7a87735 with merge base ec35f56 ( NEW FAILURES - The following jobs have failed:
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. |
SS-JIA
added a commit
that referenced
this pull request
Aug 4, 2025
## Changes Update (almost) all operators use `DynamicDispatchNode` instead of `DispatchNode`. ## Context `DynamicDispatchNode` was introduced in order to provide a way for operators to adjust 1. Which compute shader to dispatch 2. What global work group size to use 3. What local work group size to use Based on the current input and output shapes. This is useful for making sure that the most optimal compute shader is used for the current tensor sizes, and minimizing the number of inactive shader invocations. Differential Revision: [D79564595](https://our.internmc.facebook.com/intern/diff/D79564595/) ghstack-source-id: 300552325 Pull Request resolved: #13098
meta-cla
bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D79564595 |
This PR needs a
|
## Changes Update (almost) all operators use `DynamicDispatchNode` instead of `DispatchNode`. ## Context `DynamicDispatchNode` was introduced in order to provide a way for operators to adjust 1. Which compute shader to dispatch 2. What global work group size to use 3. What local work group size to use Based on the current input and output shapes. This is useful for making sure that the most optimal compute shader is used for the current tensor sizes, and minimizing the number of inactive shader invocations. Differential Revision: [D79564595](https://our.internmc.facebook.com/intern/diff/D79564595/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D79564595 |
SS-JIA
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
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):
DynamicDispatchNode#13119DynamicDispatchNode#13098get_tensor()API protected #13097vTensorPtrandget_tensor#13096Changes
Update (almost) all operators use
DynamicDispatchNodeinstead ofDispatchNode.Context
DynamicDispatchNodewas introduced in order to provide a way for operators to adjustBased on the current input and output shapes. This is useful for making sure that the most optimal compute shader is used for the current tensor sizes, and minimizing the number of inactive shader invocations.
Differential Revision: D79564595