lqs1
February 23, 2023, 3:12am
1
For example, I’m in official 22.12 docker . I want to upgrade TensorRT to 8.5.2.2 like official 23.01 docker . Is there anyway except run another 23.01 docker?
I want to do this because since 23.01 docker, the cuda toolkit version is 12.0, which causes host with cuda driver 11.x incompatible. For example, I have a host with cuda driver 11.x, when I run into docker 23.01, the pytorch is not working and reports cuda incompatible error. Since this host machine is not my personal, I don’t have access to upgrade the cuda driver…
NVES
February 23, 2023, 3:37am
2
Hi ,
These support matrices provide a look into the supported platforms, features, and hardware capabilities of the NVIDIA TensorRT 8.5.3 APIs, parsers, and layers.
You can refer below link for all the supported operators list.
<!--- SPDX-License-Identifier: Apache-2.0 -->
# Supported ONNX Operators
TensorRT 8.5 supports operators up to Opset 17. Latest information of ONNX operators can be found [here](https://github.com/onnx/onnx/blob/master/docs/Operators.md)
TensorRT supports the following ONNX data types: DOUBLE, FLOAT32, FLOAT16, INT8, and BOOL
> Note: There is limited support for INT32, INT64, and DOUBLE types. TensorRT will attempt to cast down INT64 to INT32 and DOUBLE down to FLOAT, clamping values to `+-INT_MAX` or `+-FLT_MAX` if necessary.
See below for the support matrix of ONNX operators in ONNX-TensorRT.
## Operator Support Matrix
| Operator | Supported | Supported Types | Restrictions |
|---------------------------|------------|-----------------|------------------------------------------------------------------------------------------------------------------------|
| Abs | Y | FP32, FP16, INT32 |
| Acos | Y | FP32, FP16 |
| Acosh | Y | FP32, FP16 |
| Add | Y | FP32, FP16, INT32 |
show original
Thanks!