Add tensor quantization #1963
Merged
Add tensor quantization #1963
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
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #1963 +/- ##
==========================================
- Coverage 85.29% 85.15% -0.15%
==========================================
Files 798 804 +6
Lines 95512 96050 +538
==========================================
+ Hits 81471 81788 +317
- Misses 14041 14262 +221 ☔ View full report in Codecov by Sentry. |
nathanielsimard
approved these changes
Jul 4, 2024
Comment on lines
90
to
96
| TensorPrimitive::Float(B::inner(tensor.tensor())) | ||
| } | ||
|
|
||
| fn from_inner<const D: usize>( | ||
| inner: <Self::InnerKind as TensorKind<<B as AutodiffBackend>::InnerBackend>>::Primitive<D>, | ||
| ) -> <Self as TensorKind<B>>::Primitive<D> { | ||
| B::from_inner(inner) | ||
| TensorPrimitive::Float(B::from_inner(inner.tensor())) |
There was a problem hiding this comment.
We will need to implement a q_inner and q_from_inner at some point.
There was a problem hiding this comment.
Oh, this should be fairly straightforward. I'll add it.
|
Not sure what's up with the wgpu tests, they seem to be failing intermittently even on main |
Working on it |
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Outdated suggestions cannot be applied.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.
Checklist
run-checks allscript has been executed.Related Issues/PRs
Progress towards #464
Changes
Support for static per-tensor quantization.
DType::QFloatQuantizedTensorPrimitiveQTensorOpsforquantize/dequantizeopsTensorPrimitiveenum for float tensors to include float and qfloat (quantized type).tensor()(dequantized) before calling the backend implementation on theFloatTensorPrimitiveQuantizationStrategyenum with per-tensor affine and symmetric int8 quantizationNote: QAT support should be added in a future PR
Testing
Added unit tests for affine and symmetric per-tensor quantization