memory efficient fq: use it everywhere, delete the old version #51159
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
Summary: This PR is the cleanup after #50561. High level, we make the new definition of fake_quant be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point `fake_quantize_per_tensor_affine`'s implementation to be `fake_quantize_per_tensor_affine_cachemask` 2. delete the `fake_quantize_per_tensor_affine` backward, autograd will automatically use the cachemask backward 3. delete all the `fake_quantize_per_tensor_affine` kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` performance testing was done in the previous PR. Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Jan 27, 2021
Summary: This PR is the cleanup after #50561. High level, we make the new definition of fake_quant be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point `fake_quantize_per_tensor_affine`'s implementation to be `fake_quantize_per_tensor_affine_cachemask` 2. delete the `fake_quantize_per_tensor_affine` backward, autograd will automatically use the cachemask backward 3. delete all the `fake_quantize_per_tensor_affine` kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` performance testing was done in the previous PR. Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 1adb5b962a25dd5f89c035e7855fb8eb28bb1706 Pull Request resolved: #51159
💊 CI failures summary and remediationsAs of commit 6f97b53 (more details on the Dr. CI page):
This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions to the (internal) Dr. CI Users group. |
jerryzh168
approved these changes
Jan 27, 2021
…sion" Summary: This PR is the cleanup after #50561. High level, we make the new definition of fake_quant be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point `fake_quantize_per_tensor_affine`'s implementation to be `fake_quantize_per_tensor_affine_cachemask` 2. delete the `fake_quantize_per_tensor_affine` backward, autograd will automatically use the cachemask backward 3. delete all the `fake_quantize_per_tensor_affine` kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` performance testing was done in the previous PR. Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D26090869](https://our.internmc.facebook.com/intern/diff/D26090869) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Jan 27, 2021
Summary: This PR is the cleanup after #50561. High level, we make the new definition of fake_quant be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point `fake_quantize_per_tensor_affine`'s implementation to be `fake_quantize_per_tensor_affine_cachemask` 2. delete the `fake_quantize_per_tensor_affine` backward, autograd will automatically use the cachemask backward 3. delete all the `fake_quantize_per_tensor_affine` kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` performance testing was done in the previous PR. Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: de70258e9950f1e7a401c52b7fa2082390319690 Pull Request resolved: #51159
Codecov Report
@@ Coverage Diff @@
## gh/vkuzo/214/base #51159 +/- ##
==================================================
Coverage 80.88% 80.88%
==================================================
Files 1931 1931
Lines 210604 210587 -17
==================================================
- Hits 170343 170339 -4
+ Misses 40261 40248 -13 |
|
This pull request has been merged in 0335222. |
vkuzo
added a commit
that referenced
this pull request
Jan 28, 2021
Summary: This PR is the cleanup after #51159. High level, we make the new definition of fake_quant per channel be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point fake_quantize_per_channel_affine's implementation to be fake_quantize_per_channel_affine_cachemask 2. delete the fake_quantize_per_channel_affine backward, autograd will automatically use the cachemask backward 3. delete all the fake_quantize_per_channel_affine kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Jan 28, 2021
… old version" Summary: This PR is the cleanup after #51159. High level, we make the new definition of fake_quant per channel be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point fake_quantize_per_channel_affine's implementation to be fake_quantize_per_channel_affine_cachemask 2. delete the fake_quantize_per_channel_affine backward, autograd will automatically use the cachemask backward 3. delete all the fake_quantize_per_channel_affine kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Jan 28, 2021
Summary: This PR is the cleanup after #51159. High level, we make the new definition of fake_quant per channel be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point fake_quantize_per_channel_affine's implementation to be fake_quantize_per_channel_affine_cachemask 2. delete the fake_quantize_per_channel_affine backward, autograd will automatically use the cachemask backward 3. delete all the fake_quantize_per_channel_affine kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 098b9cbf00efcd7d911d3d1df008e3be720429a8 Pull Request resolved: #51265
facebook-github-bot
pushed a commit
that referenced
this pull request
Jan 29, 2021
#51265) Summary: Pull Request resolved: #51265 This PR is the cleanup after #51159. High level, we make the new definition of fake_quant per channel be the definition used by autograd, but keep the old function around as a thin wrapper to keep the user facing API the same. In detail: 1. point fake_quantize_per_channel_affine's implementation to be fake_quantize_per_channel_affine_cachemask 2. delete the fake_quantize_per_channel_affine backward, autograd will automatically use the cachemask backward 3. delete all the fake_quantize_per_channel_affine kernels, since they are no longer used by anything Test Plan: ``` python test/test_quantization.py TestFakeQuantize ``` Imported from OSS Reviewed By: jerryzh168 Differential Revision: D26120957 fbshipit-source-id: 264426435fabd925decf6d1f0aa79275977ea29b
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:
Summary:
This PR is the cleanup after #50561. High level, we make the new
definition of fake_quant be the definition used by autograd, but keep the old
function around as a thin wrapper to keep the user facing API the same.
In detail:
fake_quantize_per_tensor_affine's implementation to befake_quantize_per_tensor_affine_cachemaskfake_quantize_per_tensor_affinebackward, autograd will automatically use the cachemask backwardfake_quantize_per_tensor_affinekernels, since they are no longer used by anythingTest Plan:
performance testing was done in the previous PR.
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D26090869