Add attribute output_dtype to QuantizeLinear #5956
Merged
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
|
@gramalingam following up on our discussion in the Operators SIG meeting yesterday, here are the changes for #5943. |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #5956 +/- ##
=======================================
Coverage 56.79% 56.79%
=======================================
Files 506 506
Lines 30308 30349 +41
Branches 4580 4589 +9
=======================================
+ Hits 17214 17238 +24
- Misses 12267 12283 +16
- Partials 827 828 +1 ☔ View full report in Codecov by Sentry. |
Comment on lines
+39
to
+42
| ONNX_ASSERTM( | ||
| false, | ||
| "Attribute output_dtype is not supported for Opset Version %d, supply a zero-point tensor instead", | ||
| target_version().version()) |
Check notice
Code scanning / CodeQL
Too many arguments to formatting function
gramalingam
reviewed
Feb 23, 2024
gramalingam
reviewed
Feb 23, 2024
gramalingam
approved these changes
Feb 23, 2024
The purpose of this change is to allow setting the quantized type without providing the zero-point tensor. This reduces model size, most importantly for block quantization where the zero-point tensor dimensions are large. It also simplifies the creation of symmetric quantization nodes. Signed-off-by: Gal Hubara Agam <ghubaraagam@nvidia.com>
Signed-off-by: Gal Hubara Agam <ghubaraagam@nvidia.com>
Signed-off-by: Gal Hubara Agam <ghubaraagam@nvidia.com>
Signed-off-by: Gal Hubara Agam <ghubaraagam@nvidia.com>
1e26f28 to
05b222a
Compare
isdanni
pushed a commit
to isdanni/onnx
that referenced
this pull request
Mar 18, 2024
The purpose of this change is to allow setting the quantized type without providing the zero-point tensor for symmetric quantization. This reduces model size, most importantly for block quantization where the zero-point tensor dimensions are large, and reduces backend runtime. This implements issue onnx#5943 --------- Signed-off-by: Gal Hubara Agam <ghubaraagam@nvidia.com> Signed-off-by: isdanni <leedanni@gmail.com>
linshokaku
pushed a commit
to linshokaku/onnx
that referenced
this pull request
Oct 2, 2024
The purpose of this change is to allow setting the quantized type without providing the zero-point tensor for symmetric quantization. This reduces model size, most importantly for block quantization where the zero-point tensor dimensions are large, and reduces backend runtime. This implements issue onnx#5943 --------- Signed-off-by: Gal Hubara Agam <ghubaraagam@nvidia.com> Signed-off-by: Linsho Kaku <linsho@preferred.jp>
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.
The purpose of this change is to allow setting the quantized type without providing the zero-point tensor for symmetric quantization.
This reduces model size, most importantly for block quantization where the zero-point tensor dimensions are large, and reduces backend runtime.
This implements issue #5943