diff options
| author | Jerry Zhang <jerryzh@fb.com> | 2019-04-03 13:13:26 -0700 |
|---|---|---|
| committer | Facebook Github Bot <facebook-github-bot@users.noreply.github.com> | 2019-04-03 13:17:11 -0700 |
| commit | dfcd7b0185d479f186ddb100c761f4df3495f8e8 (patch) | |
| tree | c28bf875351cc98565b7b9c33e7f1e056d2a5f54 /docs | |
| parent | 3af2d6d904bf1fc6d14ceb7cf8eb7bb60148b679 (diff) | |
| download | pytorch-dfcd7b0185d479f186ddb100c761f4df3495f8e8.tar.gz pytorch-dfcd7b0185d479f186ddb100c761f4df3495f8e8.tar.bz2 pytorch-dfcd7b0185d479f186ddb100c761f4df3495f8e8.zip | |
QTensor (#18230)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/18230
Implementing minimum qtensor API to unblock other workstreams in quantization
Changes:
- Added Quantizer which represents different quantization schemes
- Added qint8 as a data type for QTensor
- Added a new ScalarType QInt8
- Added QTensorImpl for QTensor
- Added following user facing APIs
- quantize_linear(scale, zero_point)
- dequantize()
- q_scale()
- q_zero_point()
Reviewed By: dzhulgakov
Differential Revision: D14524641
fbshipit-source-id: c1c0ae0978fb500d47cdb23fb15b747773429e6c
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/source/tensors.rst | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/docs/source/tensors.rst b/docs/source/tensors.rst index b9ad547411..68d6997c96 100644 --- a/docs/source/tensors.rst +++ b/docs/source/tensors.rst @@ -205,6 +205,7 @@ view of a storage and defines numeric operations on it. .. automethod:: cumprod .. automethod:: cumsum .. automethod:: data_ptr + .. automethod:: dequantize .. automethod:: det .. automethod:: dense_dim .. automethod:: detach @@ -354,6 +355,9 @@ view of a storage and defines numeric operations on it. .. automethod:: pstrf .. automethod:: put_ .. automethod:: qr + .. automethod:: quantize_linear + .. automethod:: q_scale + .. automethod:: q_zero_point .. automethod:: random_ .. automethod:: reciprocal .. automethod:: reciprocal_ |