mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-07 12:21:27 +01:00
3064bc4060
In PR #93822 the `fx2trt` backend was removed which registered the `tensorrt` backend names to point to `fx2trt` / `torch_tensorrt` and move the name to `onnxrt`. We want to reserve the name `tensorrt` for `torch_tensorrt` to prevent any confusion but due to code-freeze we cannot complete the integration and set up testing for the next release. So we propose leaving out the `tensorrt` name until we can set up the backend and testing for it. Pull Request resolved: https://github.com/pytorch/pytorch/pull/94632 Approved by: https://github.com/frank-wei
13 lines
383 B
Python
13 lines
383 B
Python
# import torch # type: ignore[import]
|
|
# from .common import device_from_inputs, fake_tensor_unsupported # type: ignore[import]
|
|
# from .registry import register_backend # type: ignore[import]
|
|
|
|
"""
|
|
Placeholder for TensorRT backend for dynamo via torch-tensorrt
|
|
"""
|
|
|
|
# @register_backend
|
|
# def tensorrt(gm, example_inputs):
|
|
# import torch_tensorrt # type: ignore[import]
|
|
# pass
|