Create a quantized in-palce version CUDA ReLU function, relu_quantized_cuda_. #85670

fufeisi · 2022-09-26T21:59:36Z

Stack from ghstack (oldest at bottom):

-> Create a quantized in-palce version CUDA ReLU function, relu_quantized_cuda_. #85670
Summary:
this and Create a quantized non-in-palce version CUDA ReLU function, #85669 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda.
Test Plan:
python test/test_quantization.py

Previous PR that has been reverted: #85502.

…d_cuda_. [ghstack-poisoned]

pytorch-bot · 2022-09-26T21:59:38Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/85670

📄 Preview Python docs built from this PR
📄 Preview C++ docs built from this PR
❓ Need help or want to give feedback on the CI? Visit our office hours

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures, 1 Pending

As of commit a37676b:
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

…d_cuda_. ghstack-source-id: a37dd66 Pull Request resolved: #85670

…lu_quantized_cuda_." [ghstack-poisoned]

…lu_quantized_cuda_." Summary: this and #85669 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py [ghstack-poisoned]

…d_cuda_. ghstack-source-id: 86538fb Pull Request resolved: #85670

…lu_quantized_cuda_." Summary: this and #85669 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py [ghstack-poisoned]

…d_cuda_. ghstack-source-id: b5dfb4d Pull Request resolved: #85670

dzdang · 2022-09-28T16:20:23Z

can you link the previous PR (the one with the review history) in the summary

dzdang · 2022-09-28T17:46:37Z

test/quantization/core/test_quantized_op.py

        ]
        devices = ["cpu", "cuda"] if TEST_CUDA else ["cpu"]
        for device in devices:
-            # Only test the non-in-place version relu quantized cuda,


thought I left a review comment here but can't find it. I'm wondering why we add this in the previous PR and remove it here?

For the previous PR, we only have non-in-palce qrelu, so I add this for only test non-in-palce qrelu, avoid in-palce qrelu.

…lu_quantized_cuda_." Summary: this and #85669 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

…DA ReLU function," Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

…lu_quantized_cuda_." Summary: this and #85669 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

…DA ReLU function," Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

…d_cuda_. ghstack-source-id: 78e0f85 Pull Request resolved: #85670

fufeisi · 2022-09-28T20:57:36Z

@ pytorchbot rebase

…DA ReLU function," Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

fufeisi · 2022-09-29T01:08:49Z

@pytorchbot rebase

pytorchmergebot · 2022-09-29T01:10:45Z

@pytorchbot successfully started a rebase job. Check the current status here

pytorchmergebot · 2022-09-29T01:10:55Z

Rebase failed due to

Raised by https://github.com/pytorch/pytorch/actions/runs/3147958597

Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. Pull Request resolved: #85669 Approved by: https://github.com/dzdang

fufeisi · 2022-09-29T05:58:00Z

@pytorchbot rebase

pytorchmergebot · 2022-09-29T05:59:33Z

@pytorchbot successfully started a rebase job. Check the current status here

pytorchmergebot · 2022-09-29T05:59:39Z

Rebase failed due to

Raised by https://github.com/pytorch/pytorch/actions/runs/3148960359

…lu_quantized_cuda_." Summary: this and #85669 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. [ghstack-poisoned]

…d_cuda_. ghstack-source-id: 3609dc4 Pull Request resolved: #85670

fufeisi · 2022-09-30T17:36:41Z

@pytorchbot merge

pytorchmergebot · 2022-09-30T17:38:24Z

@pytorchbot successfully started a merge job. Check the current status here.
The merge job was triggered without a flag. This means that your change will be merged once all checks on your PR have passed (ETA: 0-4 Hours). If this is not the intended behavior, feel free to use some of the other merge options in the wiki.
Please reach out to the PyTorch DevX Team with feedback or questions!

github-actions · 2022-09-30T17:39:13Z

Hey @fufeisi.
You've committed this PR, but it does not have both a 'release notes: ...' and 'topics: ...' label. Please add one of each to the PR. The 'release notes: ...' label should represent the part of PyTorch that this PR changes (fx, autograd, distributed, etc) and the 'topics: ...' label should represent the kind of PR it is (not user facing, new feature, bug fix, perf improvement, etc). The list of valid labels can be found here for the 'release notes: ...' and here for the 'topics: ...'.
For changes that are 'topic: not user facing' there is no need for a release notes label.

Summary: this and #85670 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. Pull Request resolved: #85669 Approved by: https://github.com/dzdang

…d_cuda_. (#85670) Summary: this and #85669 are to allow the relu function to run on a quantized tensor on cuda. That is torch.relu(qa) for a quantized tensor qa on cuda. Test Plan: python test/test_quantization.py Previous PR that has been reverted: #85502. Pull Request resolved: #85670 Approved by: https://github.com/dzdang, https://github.com/z-a-f

Create a quantized in-palce version CUDA ReLU function, relu_quantize…

da6c557

…d_cuda_. [ghstack-poisoned]

fufeisi requested review from jerryzh168, z-a-f, vkuzo and dzdang as code owners September 26, 2022 21:59

fufeisi mentioned this pull request Sep 26, 2022

Create a quantized non-in-palce version CUDA ReLU function, #85669

Closed

pytorch-bot bot added the release notes: quantization release notes category label Sep 26, 2022

facebook-github-bot added the cla signed label Sep 26, 2022

fufeisi added a commit that referenced this pull request Sep 26, 2022

Create a quantized in-palce version CUDA ReLU function, relu_quantize…

3b60bbe

…d_cuda_. ghstack-source-id: a37dd66 Pull Request resolved: #85670

fufeisi added the ciflow/trunk Trigger trunk jobs on your pull request label Sep 26, 2022

Update on "Create a quantized in-palce version CUDA ReLU function, re…

0b707f3

…lu_quantized_cuda_." [ghstack-poisoned]

fufeisi added a commit that referenced this pull request Sep 27, 2022

Create a quantized in-palce version CUDA ReLU function, relu_quantize…

b525bb8

…d_cuda_. ghstack-source-id: 86538fb Pull Request resolved: #85670

fufeisi added a commit that referenced this pull request Sep 28, 2022

Create a quantized in-palce version CUDA ReLU function, relu_quantize…

540b5c8

…d_cuda_. ghstack-source-id: b5dfb4d Pull Request resolved: #85670

dzdang approved these changes Sep 28, 2022

View reviewed changes

z-a-f approved these changes Sep 28, 2022

View reviewed changes

dzdang reviewed Sep 28, 2022

View reviewed changes

fufeisi added a commit that referenced this pull request Sep 28, 2022

Create a quantized in-palce version CUDA ReLU function, relu_quantize…

4b2e2f8

…d_cuda_. ghstack-source-id: 78e0f85 Pull Request resolved: #85670

fufeisi added a commit that referenced this pull request Sep 29, 2022

Create a quantized in-palce version CUDA ReLU function, relu_quantize…

45a88c6

…d_cuda_. ghstack-source-id: 3609dc4 Pull Request resolved: #85670

pytorchmergebot added the Merged label Sep 30, 2022

pytorchmergebot closed this in 0a7d8b4 Sep 30, 2022

facebook-github-bot deleted the gh/fufeisi/2/head branch October 4, 2022 14:20

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Create a quantized in-palce version CUDA ReLU function, relu_quantized_cuda_. #85670

Create a quantized in-palce version CUDA ReLU function, relu_quantized_cuda_. #85670

Uh oh!

fufeisi commented Sep 26, 2022 •

edited

Loading

Uh oh!

pytorch-bot bot commented Sep 26, 2022 •

edited

Loading

Uh oh!

dzdang commented Sep 28, 2022

Uh oh!

dzdang Sep 28, 2022

Uh oh!

fufeisi Sep 28, 2022

Uh oh!

fufeisi commented Sep 28, 2022 •

edited

Loading

Uh oh!

fufeisi commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

fufeisi commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

fufeisi commented Sep 30, 2022

Uh oh!

pytorchmergebot commented Sep 30, 2022

Uh oh!

github-actions bot commented Sep 30, 2022

Uh oh!

Uh oh!

Create a quantized in-palce version CUDA ReLU function, relu_quantized_cuda_. #85670

Create a quantized in-palce version CUDA ReLU function, relu_quantized_cuda_. #85670

Uh oh!

Conversation

fufeisi commented Sep 26, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Sep 26, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/85670

✅ No Failures, 1 Pending

Uh oh!

dzdang commented Sep 28, 2022

Uh oh!

dzdang Sep 28, 2022

Choose a reason for hiding this comment

Uh oh!

fufeisi Sep 28, 2022

Choose a reason for hiding this comment

Uh oh!

fufeisi commented Sep 28, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

fufeisi commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

fufeisi commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

pytorchmergebot commented Sep 29, 2022

Uh oh!

fufeisi commented Sep 30, 2022

Uh oh!

pytorchmergebot commented Sep 30, 2022

Uh oh!

github-actions bot commented Sep 30, 2022

Uh oh!

Uh oh!

fufeisi commented Sep 26, 2022 •

edited

Loading

pytorch-bot bot commented Sep 26, 2022 •

edited

Loading

fufeisi commented Sep 28, 2022 •

edited

Loading