You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
| Linux aarch64 / GPU | **Native Compilation Supported on JetPack-4.4+ (use v1.0.0 for the time being)** |
110
-
| Linux aarch64 / DLA | **Native Compilation Supported on JetPack-4.4+ (use v1.0.0 for the time being)** |
111
+
| Linux Jetson / GPU | **Source Compilation Supported on JetPack-4.4+** |
112
+
| Linux Jetson / DLA | **Source Compilation Supported on JetPack-4.4+** |
111
113
| Linux ppc64le / GPU | Not supported |
112
114
113
115
> Note: Refer [NVIDIA L4T PyTorch NGC container](https://ngc.nvidia.com/catalog/containers/nvidia:l4t-pytorch) for PyTorch libraries on JetPack.
@@ -116,10 +118,10 @@ auto results = trt_mod.forward({input_tensor});
116
118
117
119
These are the following dependencies used to verify the testcases. Torch-TensorRT can work with other versions, but the tests are not guaranteed to pass.
118
120
119
-
- Bazel 6.3.2
120
-
- Libtorch 2.8.0.dev (latest nightly) (built with CUDA 12.8)
0 commit comments