projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: a00d587) | patch
[fx2trt] Add dequantize support (#63448)
authorJerry Zhang <jerryzh@fb.com>
Wed, 18 Aug 2021 14:36:47 +0000 (07:36 -0700)
committerFacebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
Wed, 18 Aug 2021 14:44:17 +0000 (07:44 -0700)
commit061b36e2f58fea2ec9c06577c4bef70a4519af20
tree804a2426e044b7d4b3c7e57a9b388b56ba690cabtree | snapshot
parenta00d5878497af2a0bb599fe939369de49256b1eacommit | diff
[fx2trt] Add dequantize support (#63448)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/63448

Only available after TensorRT 8.0

Test Plan: buck run mode/opt caffe2/torch/fb/fx2trt:test_dequantize

Reviewed By: 842974287

Differential Revision: D30296863

fbshipit-source-id: 44b9630ef0d210e7f20e650dc81c519f7e41f5f3
torch/fx/experimental/fx2trt/converters/acc_ops_converters.py diff | blob | history
torch/fx/experimental/fx_acc/acc_ops.py diff | blob | history
torch/fx/experimental/graph_manipulation.py diff | blob | history
Domain: Machine Learning / ML Framework;