[ET-VK][qconv] Dynamically select between im2col path and general path#17387
Merged
meta-codesync[bot] merged 8 commits intogh/SS-JIA/418/basefrom Feb 13, 2026
Merged
[ET-VK][qconv] Dynamically select between im2col path and general path#17387meta-codesync[bot] merged 8 commits intogh/SS-JIA/418/basefrom
meta-codesync[bot] merged 8 commits intogh/SS-JIA/418/basefrom
Conversation
This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17387
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 5503158 with merge base dcfd12d ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This was referenced Feb 11, 2026
This PR needs a
|
…general path" This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
…general path" This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
…general path" This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
manuelcandales
approved these changes
Feb 12, 2026
added 4 commits
February 12, 2026 14:23
…general path" This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
…general path" This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
…general path" This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
…general path" This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/) [ghstack-poisoned]
meta-codesync
Bot
merged commit 509c974
into
gh/SS-JIA/418/base
196 of 197 checks passed
SS-JIA
pushed a commit
that referenced
this pull request
Feb 13, 2026
Pull Request resolved: #17387 This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. ghstack-source-id: 340983078 @exported-using-ghexport Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/)
SS-JIA
pushed a commit
that referenced
this pull request
Feb 13, 2026
Pull Request resolved: #17387 This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. ghstack-source-id: 340983078 @exported-using-ghexport Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/)
SS-JIA
pushed a commit
that referenced
this pull request
Feb 13, 2026
Pull Request resolved: #17387 This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. ghstack-source-id: 340983078 @exported-using-ghexport Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/)
chizkiyahu
pushed a commit
to chizkiyahu/executorch
that referenced
this pull request
Feb 23, 2026
Pull Request resolved: pytorch#17387 This adds a dispatch layer to `q8ta_conv2d` that dynamically selects between the im2col-based and general convolution implementations at graph build time. The existing `q8ta_conv2d` function is renamed to `q8ta_conv2d_general`, and a new `q8ta_conv2d` dispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path. A separate `q8ta_conv2d_general` operator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed. ghstack-source-id: 340983078 @exported-using-ghexport Differential Revision: [D93000162](https://our.internmc.facebook.com/intern/diff/D93000162/)
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
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):
This adds a dispatch layer to
q8ta_conv2dthat dynamically selects between the im2col-based and general convolution implementations at graph build time. The existingq8ta_conv2dfunction is renamed toq8ta_conv2d_general, and a newq8ta_conv2ddispatcher is introduced that chooses the im2col path when the convolution is non-grouped, has input channels divisible by 4, and kernel size ≤ 3x3. All other cases fall through to the general path.A separate
q8ta_conv2d_generaloperator is also registered so tests can directly invoke the general path for comparison. The test suite is updated to exercise both the general and im2col implementations explicitly, and the default impl_selector is changed from "general" to empty (which triggers the new dispatcher). FP buffer storage types are removed from the test matrix since they are not needed.Differential Revision: D93000162