OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

[tensorexpr][quant] Enable tensorexpr for quant,dequant

Browse Source 
ghstack-source-id: e524190fa2
Pull Request resolved: https://github.com/pytorch/pytorch/pull/71243
This commit is contained in:
Ivan Kobzarev 2022-01-31 14:35:14 -08:00
parent 41de026e8b
commit b40a47d318
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
torch/csrc/jit/tensorexpr/lowerings.cpp
View File

@ -1648,8 +1648,8 @@ int nnc_lowerings_lazy_registration() {
{"aten::embedding(Tensor weight, Tensor indices, int padding_idx=-1, bool scale_grad_by_freq=False, bool sparse=False) -> Tensor"},
computeEmbedding);
#define NNC_QUANTIZATION_EXPR_QUANT 0
#define NNC_QUANTIZATION_EXPR_DEQUANT 0
#define NNC_QUANTIZATION_EXPR_QUANT 1
#define NNC_QUANTIZATION_EXPR_DEQUANT 1
RegisterNNCLoweringsFunction aten_quantize_per_tensor(
{"aten::quantize_per_tensor(Tensor self, float scale, int zero_point, int dtype) -> (Tensor)",