[ET-VK] Re-implement (de)quantize_per_tensor.default #15721
Merged
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
Re-implement the `quantized_decomposed.(de)quantize_per_tensor.default` ops with `add_quantize_and_pack_4w4c_node` As a consequence, the `et_vk.quantize_q8ta_for_conv2d.default` and `et_vk.dequantize_q8to_from_conv2d.default` ops are not needed anymore. The overall goal is to streamline the quantize/dequantize interface in ET-VK. Differential Revision: [D86702457](https://our.internmc.facebook.com/intern/diff/D86702457/) [ghstack-poisoned]
This was referenced Nov 10, 2025
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15721
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 62fdd2e with merge base aba44fd ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Nov 10, 2025
SS-JIA
pushed a commit
that referenced
this pull request
Nov 10, 2025
Re-implement the `quantized_decomposed.(de)quantize_per_tensor.default` ops with `add_quantize_and_pack_4w4c_node` As a consequence, the `et_vk.quantize_q8ta_for_conv2d.default` and `et_vk.dequantize_q8to_from_conv2d.default` ops are not needed anymore. The overall goal is to streamline the quantize/dequantize interface in ET-VK. Differential Revision: [D86702457](https://our.internmc.facebook.com/intern/diff/D86702457/) ghstack-source-id: 322214458 Pull Request resolved: #15721
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
manuelcandales
approved these changes
Nov 11, 2025
SS-JIA
pushed a commit
that referenced
this pull request
Nov 11, 2025
Re-implement the `quantized_decomposed.(de)quantize_per_tensor.default` ops with `add_quantize_and_pack_4w4c_node` As a consequence, the `et_vk.quantize_q8ta_for_conv2d.default` and `et_vk.dequantize_q8to_from_conv2d.default` ops are not needed anymore. The overall goal is to streamline the quantize/dequantize interface in ET-VK. Differential Revision: [D86702457](https://our.internmc.facebook.com/intern/diff/D86702457/) ghstack-source-id: 322214458 Pull Request resolved: #15721
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):
Re-implement the
quantized_decomposed.(de)quantize_per_tensor.defaultops withadd_quantize_and_pack_4w4c_nodeAs a consequence, the
et_vk.quantize_q8ta_for_conv2d.defaultandet_vk.dequantize_q8to_from_conv2d.defaultops are not needed anymore.The overall goal is to streamline the quantize/dequantize interface in ET-VK.
Differential Revision: D86702457