[ET-VK] Allow int4 linear to execute without 8bit buffer support #10030
+56
−30
Conversation
This file contains 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
## Context Some Vulkan devices do not have support for 8-bit buffers, which is currently required to execute the int4 linear compute shader due to the prepacking shader requiring it. This diff bypasses that restriction by introducing a variant of the prepacking shader that does not need 8-bit buffers. ## Changes Introduce a variant of the int4 weight prepacking shader that interprets the tensor data as an array of `uint` instead of `uint8_t`. Each `uint` represents 4 `uint8_t` values. Differential Revision: [D72750897](https://our.internmc.facebook.com/intern/diff/D72750897/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10030
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 92f11a3 with merge base 6d1caca ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
SS-JIA
added a commit
that referenced
this pull request
Apr 9, 2025
## Context Some Vulkan devices do not have support for 8-bit buffers, which is currently required to execute the int4 linear compute shader due to the prepacking shader requiring it. This diff bypasses that restriction by introducing a variant of the prepacking shader that does not need 8-bit buffers. ## Changes Introduce a variant of the int4 weight prepacking shader that interprets the tensor data as an array of `uint` instead of `uint8_t`. Each `uint` represents 4 `uint8_t` values. Differential Revision: [D72750897](https://our.internmc.facebook.com/intern/diff/D72750897/) ghstack-source-id: 277173967 Pull Request resolved: #10030
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D72750897 |
…upport" ## Context Some Vulkan devices do not have support for 8-bit buffers, which is currently required to execute the int4 linear compute shader due to the prepacking shader requiring it. This diff bypasses that restriction by introducing a variant of the prepacking shader that does not need 8-bit buffers. ## Changes Introduce a variant of the int4 weight prepacking shader that interprets the tensor data as an array of `uint` instead of `uint8_t`. Each `uint` represents 4 `uint8_t` values. Differential Revision: [D72750897](https://our.internmc.facebook.com/intern/diff/D72750897/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 9, 2025
Pull Request resolved: #10030 ## Context Some Vulkan devices do not have support for 8-bit buffers, which is currently required to execute the int4 linear compute shader due to the prepacking shader requiring it. This diff bypasses that restriction by introducing a variant of the prepacking shader that does not need 8-bit buffers. ## Changes Introduce a variant of the int4 weight prepacking shader that interprets the tensor data as an array of `uint` instead of `uint8_t`. Each `uint` represents 4 `uint8_t` values. Differential Revision: [D72750897](https://our.internmc.facebook.com/intern/diff/D72750897/) ghstack-source-id: 277175676
|
This pull request was exported from Phabricator. Differential Revision: D72750897 |
…upport" ## Context Some Vulkan devices do not have support for 8-bit buffers, which is currently required to execute the int4 linear compute shader due to the prepacking shader requiring it. This diff bypasses that restriction by introducing a variant of the prepacking shader that does not need 8-bit buffers. ## Changes Introduce a variant of the int4 weight prepacking shader that interprets the tensor data as an array of `uint` instead of `uint8_t`. Each `uint` represents 4 `uint8_t` values. Differential Revision: [D72750897](https://our.internmc.facebook.com/intern/diff/D72750897/) [ghstack-poisoned]
This was referenced Apr 15, 2025
|
This pull request was exported from Phabricator. Differential Revision: D72750897 |
trivedivivek
approved these changes
Apr 15, 2025
facebook-github-bot
merged commit 3aa73e9
into
gh/SS-JIA/210/base
84 of 85 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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):
Context
Some Vulkan devices do not have support for 8-bit buffers, which is currently required to execute the int4 linear compute shader due to the prepacking shader requiring it.
This diff bypasses that restriction by introducing a variant of the prepacking shader that does not need 8-bit buffers.
Changes
Introduce a variant of the int4 weight prepacking shader that interprets the tensor data as an array of
uintinstead ofuint8_t. Eachuintrepresents 4uint8_tvalues.Differential Revision: D72750897