-
Notifications
You must be signed in to change notification settings - Fork 3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
failing to find trt_timing_cache_path #21484
Comments
Which ORT version you were using? |
idk how to check that, i only followed a guide. if you can guide me trough it, for sure i will provide the information your requesting, for my understaing regarding the issue the "trt_cache_path" is or not specified or wrong typed. And thats part of the configuration of onnxruntime, is what copilot said xD but i dont know how to fix that i have been looking for a configuration file but i cant find any. So bcoz the path is not specified (probably) bcoz i only copy and paste files tensorrt is failing so is using cude - cpu for sure the path is wrong if i could know what file is maybe i could fix it or just replace it, probably if i do will screw something else. So i rather leave it the way it is and just edit or fix what is requesting. |
This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details. |
hello im trying to use tensorrt and when looking for the trt path cache, while processing.
is giving me this error
Error D:\a_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:709 onnxruntime::python::CreateExecutionProviderInstance Invalid TensorRT EP option: trt_timing_cache_path
when using [('TensorrtExecutionProvider', {'trt_engine_cache_enable': True, 'trt_engine_cache_path': 'tensorrt-engines', 'trt_timing_cache_enable': True, 'trt_timing_cache_path': 'tensorrt-engines', 'trt_dump_ep_context_model': True, 'trt_ep_context_file_path': 'tensorrt-engines', 'trt_layer_norm_fp32_fallback': True, 'trt_builder_optimization_level': 5}), 'CUDAExecutionProvider', 'CPUExecutionProvider']
Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.
it seems to be or that i put the wrong path or maybe i just miss typed something
can someone help me a bit please'??
The text was updated successfully, but these errors were encountered: