[PyTorch Edge] Add Quantized Softmax Op (Naive Implementation) #75017
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
Summary: This version just does dequantize, fp32 softmax, quantize. Another version of actual quantized softmax using qnnpack will be added next Test Plan: From fbcode: ```buck test caffe2/test:quantization -- test_qsoftmax``` Benchmarking: See summary of D34996486 Reviewed By: kimishpatel Differential Revision: D34943147 fbshipit-source-id: dcebecd55e8da989ab4937c2b8db38baaf32b700
Contributor
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit 1e34275 (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D34943147 |
facebook-github-bot
pushed a commit
that referenced
this pull request
Mar 31, 2022
Summary: Pull Request resolved: #75017 This version just does dequantize, fp32 softmax, quantize. Another version of actual quantized softmax using qnnpack will be added next Test Plan: From fbcode: ```buck test caffe2/test:quantization -- test_qsoftmax``` Benchmarking: See summary of D34996486 Reviewed By: kimishpatel Differential Revision: D34943147 fbshipit-source-id: 426a0780803597a21460139c67960891d6e9cc81
Contributor
|
Hey @salilsdesai. |
vkuzo
added a commit
that referenced
this pull request
Apr 1, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the eager mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. A future PR will add FX graph mode workflow integration. Test plan: ``` python test/test_quantization.py TestQuantizeEagerPTQStatic.test_softmax ``` [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 1, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 1, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 1, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 1, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: 097b951 Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 4, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 4, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 4, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: 0af2cec Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 4, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 4, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: 9eb7056 Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 4, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 4, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: e555ffe Pull Request resolved: #75106
Contributor
|
This pull request has been reverted by 1bcae0d. To re-land this change, please open another pull request, assignthe same reviewers, fix the CI failures that caused the revert and make sure that the failing CI runs on the PR by applying the proper ciflow label (e.g., ciflow/trunk). |
Contributor
|
This pull request has been reverted by b99b7182aeaf77d07978708b3e1630260e342974. To re-land this change, please open another pull request, assignthe same reviewers, fix the CI failures that caused the revert and make sure that the failing CI runs on the PR by applying the proper ciflow label (e.g., ciflow/trunk). |
vkuzo
added a commit
that referenced
this pull request
Apr 13, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: 9ec762e Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 13, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 13, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 13, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: 8dec27f Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 14, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: 535666a Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 14, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 19, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 19, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: 7d83ed1 Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 20, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` ghstack-source-id: f45b660 Pull Request resolved: #75106
vkuzo
added a commit
that referenced
this pull request
Apr 20, 2022
Summary: In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Differential Revision: [D35324817](https://our.internmc.facebook.com/intern/diff/D35324817) [ghstack-poisoned]
facebook-github-bot
pushed a commit
that referenced
this pull request
Apr 20, 2022
Summary: Pull Request resolved: #75106 In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test Plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Reviewed By: kimishpatel, andrewor14 Differential Revision: D35324817 Pulled By: vkuzo fbshipit-source-id: 710ae3bedf8a6ad1dc411cd9808fdd0ce743e757
pytorchmergebot
pushed a commit
that referenced
this pull request
Apr 20, 2022
Summary: Pull Request resolved: #75106 In #75017 a quantized softmax kernel was added. This PR adds the FX graph mode quantization workflow integration to swap `nn.Softmax` to `nnq.Softmax`. Test Plan: ``` python test/test_quantization.py TestQuantizeFxOps.test_fixed_qparams_ops ``` Reviewed By: kimishpatel, andrewor14 Differential Revision: D35324817 Pulled By: vkuzo fbshipit-source-id: 710ae3bedf8a6ad1dc411cd9808fdd0ce743e757 (cherry picked from commit d67603c)
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.
Summary:
This version just does dequantize, fp32 softmax, quantize.
Another version of actual quantized softmax using qnnpack will be added next
Test Plan:
From fbcode:
buck test caffe2/test:quantization -- test_qsoftmaxBenchmarking: See summary of D34996486
Reviewed By: kimishpatel
Differential Revision: D34943147