Allow per-channel QTensor accept any floating type for scales #26676
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
[ghstack-poisoned]
pytorchbot
added
module: operators
oncall: quantization
This was referenced Sep 23, 2019
dzhulgakov
pushed a commit
that referenced
this pull request
Sep 23, 2019
ghstack-source-id: ce907389799e9e68755d602accf426e2b4602a8f Pull Request resolved: #26676
…les" Just makes it more user-friendly to be able to pass any floating point or int point values to scales or zero_points for per-channel quantization. It matches behavior or per tensor quantizer where those arguments are scalars (not tensors) and thus automatic casting is applied. Differential Revision: [D17537051](https://our.internmc.facebook.com/intern/diff/D17537051) [ghstack-poisoned]
dzhulgakov
pushed a commit
that referenced
this pull request
Sep 24, 2019
ghstack-source-id: 180dd4918ed33d0b776e4ea34e7b1e2a3896600d Pull Request resolved: #26676
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Sep 24, 2019
Summary: Pull Request resolved: pytorch/pytorch#26676 Just makes it more user-friendly to be able to pass any floating point or int point values to scales or zero_points for per-channel quantization. It matches behavior or per tensor quantizer where those arguments are scalars (not tensors) and thus automatic casting is applied. Test Plan: Imported from OSS Differential Revision: D17537051 Pulled By: dzhulgakov fbshipit-source-id: e955ccdb5b4691828a559dc8f1ed7de54b6d12c4
|
@dzhulgakov merged this pull request in ade60f8. |
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Outdated suggestions cannot be applied.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:
Just makes it more user-friendly to be able to pass any floating point or int point values to scales or zero_points for per-channel quantization. It matches behavior or per tensor quantizer where those arguments are scalars (not tensors) and thus automatic casting is applied.
Differential Revision: D17537051