This repository was archived by the owner on Jul 1, 2025. It is now read-only.
Support quantized output in Onnxifi #4555
Closed
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
|
This pull request was exported from Phabricator. Differential Revision: D21783368 |
|
This pull request was exported from Phabricator. Differential Revision: D21783368 |
Summary: Pull Request resolved: pytorch/pytorch#39230 Pull Request resolved: pytorch#4555 With this we now support cutting in the middle of the quantized domain for Onnxifi. This will allow us to observe intermediate quantized value during Onnxifi. Input still has to be non-quantized tensor though. This will be a follow-up. Reviewed By: hyuen Differential Revision: D21783368 fbshipit-source-id: e4a58fd1c6a6a10950395fdf6dfb2a6a90ff7437
|
This pull request was exported from Phabricator. Differential Revision: D21783368 |
yinghai
pushed a commit
to yinghai/pytorch
that referenced
this pull request
Jun 2, 2020
Summary: Pull Request resolved: pytorch#39230 Pull Request resolved: pytorch/glow#4555 With this we now support cutting in the middle of the quantized domain for Onnxifi. This will allow us to observe intermediate quantized value during Onnxifi. Input still has to be non-quantized tensor though. This will be a follow-up. Test Plan: ``` buck test glow/fb/test/numerics:test_fc_nnpi_int8nnpi -- test_quantize ``` Reviewed By: hyuen Differential Revision: D21783368 fbshipit-source-id: 02a09519c9f9ebac4da6e479f473cdf755d8a074
facebook-github-bot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
Jun 2, 2020
Summary: Pull Request resolved: #39230 Pull Request resolved: pytorch/glow#4555 With this we now support cutting in the middle of the quantized domain for Onnxifi. This will allow us to observe intermediate quantized value during Onnxifi. Input still has to be non-quantized tensor though. This will be a follow-up. Test Plan: ``` buck test glow/fb/test/numerics:test_fc_nnpi_int8nnpi -- test_quantize ``` Reviewed By: hyuen Differential Revision: D21783368 fbshipit-source-id: 51001246e9e0357d7ba90bf12279b644f5f30221
|
This pull request has been merged in 01e357b. |
vdantu
pushed a commit
to vdantu/glow
that referenced
this pull request
Jul 12, 2020
Summary: Pull Request resolved: pytorch/pytorch#39230 Pull Request resolved: pytorch#4555 With this we now support cutting in the middle of the quantized domain for Onnxifi. This will allow us to observe intermediate quantized value during Onnxifi. Input still has to be non-quantized tensor though. This will be a follow-up. Reviewed By: hyuen Differential Revision: D21783368 fbshipit-source-id: 51001246e9e0357d7ba90bf12279b644f5f30221
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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: With this we now support cutting in the middle of the quantized domain for Onnxifi. This will allow us to observe intermediate quantized value during Onnxifi. Input still has to be non-quantized tensor though. This will be a follow-up.
Differential Revision: D21783368