projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 85222c0) | patch
[quant][tensorrt] Add tensorrt backend config (#64623)
authorJerry Zhang <jerryzh@fb.com>
Tue, 14 Sep 2021 22:26:03 +0000 (15:26 -0700)
committerFacebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
Tue, 14 Sep 2021 22:27:33 +0000 (15:27 -0700)
commit670853295addc9250d5829a26bd1065ff9bff159
treeafaf6bf37363548f2fea65fe8a8eb0568fdd3496tree | snapshot
parent85222c050f3fe2e2c7180f6f0aed5d0bbc7ab671commit | diff
[quant][tensorrt] Add tensorrt backend config (#64623)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/64623

The config api will change, but we'll add configs gradually for TensorRT to unblock experimentation

Test Plan:
python torch/fx/experimental/fx2trt/example/unittests.py

Imported from OSS

Reviewed By: vkuzo

Differential Revision: D30800474

fbshipit-source-id: 3c4640de1205a0f19b62943ab84f386d80394ec2
torch/fx/experimental/fx2trt/example/unittests.py [new file with mode: 0644] blob
torch/quantization/fx/__init__.py diff | blob | history
torch/quantization/fx/backend_config_dict/__init__.py diff | blob | history
torch/quantization/fx/backend_config_dict/tensorrt.py [new file with mode: 0644] blob
torch/quantization/fx/quantization_patterns.py diff | blob | history
torch/quantization/quantize_fx.py diff | blob | history
Domain: Machine Learning / ML Framework;