Open
Description
❓ Question
I follow this tutorial to install Torch-TensorRT, but in the last step:
# build and install torch_tensorrt wheel file
python setup.py --use-cxx11-abi install --user
some errors happened:
using CXX11 ABI build
Jetpack version: 6.1
building libtorchtrt cmd=['/usr/bin/bazel', 'build', '//:libtorchtrt', '--compilation_mode=opt', '--distdir=third_party/dist_dir/x86_64-linux-gnu', '--config=linux', '--platforms=//toolchains:jetpack_6.1']
DEBUG: /home/lab223/.cache/bazel/_bazel_lab223/3fb6c16c20f38dfc11e57e77e6eea473/external/rules_python~/python/private/python.bzl:46:10: WARNING: Ignoring toolchain 'python_3_11' from module 'rules_pkg': Toolchain 'python_3_11' from module 'torch_tensorrt' already registered Python version 3.11 and has precedence
INFO: Analyzed target //:libtorchtrt (127 packages loaded, 13849 targets configured).
ERROR: /home/lab223/TensorRT/core/util/BUILD:60:11: Compiling core/util/Exception.cpp failed: (Exit 1): gcc failed: error executing CppCompile command (from target //core/util:exception) /home/lab223/anaconda3/envs/rnw/bin/gcc -U_FORTIFY_SOURCE -fstack-protector -Wall -Wunused-but-set-parameter -Wno-free-nonheap-object -fno-omit-frame-pointer -g0 -O2 '-D_FORTIFY_SOURCE=1' -DNDEBUG ... (remaining 25 arguments skipped)
Use --sandbox_debug to see verbose messages from the sandbox and retain the sandbox build root for debugging
gcc: fatal error: cannot execute 'cc1plus': execvp: No such file or directory
compilation terminated.
Target //:libtorchtrt failed to build
Use --verbose_failures to see the command lines of failed build steps.
INFO: Elapsed time: 8.444s, Critical Path: 4.05s
INFO: 329 processes: 329 internal.
ERROR: Build did NOT complete successfully
Environment
Build information about Torch-TensorRT can be found by turning on debug messages
- PyTorch Version (e.g., 1.0): 2.5.0
- CPU Architecture: arm64(Jetson AGX Orin)
- OS (e.g., Linux): Linux
- How you installed PyTorch: pip
- Build command you used (if compiling from source): python setup.py --use-cxx11-abi install --user
- Are you using local sources or building from archives: building from archives
- Python version: 3.10.15
- CUDA version: 12.6
- GPU models and configuration: -
- Any other relevant information: Install torch_tensorrt in the model's anaconda virtual environment
Additional context
please help me!thanks!!!!