saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-29 20:14:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

added missing flag ORT_TENSORRT_DUMP_SUBGRAPHS (#5724)

Browse source 
[DOCUMENTATION]
added descriptionof the function ORT_TENSORRT_DUMP_SUBGRAPHS to the documentation
This commit is contained in:
Johannes Bannhofer 2020-11-06 21:32:12 +01:00 committed by GitHub
parent 92292de135
commit 6f6dd0b869
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/execution_providers/TensorRT-ExecutionProvider.md
View file

@ -70,6 +70,8 @@ There are several environment variables for TensorRT execution provider.
* ORT_TENSORRT_ENGINE_CACHE_PATH: Specify path for TensorRT engine files if ORT_TENSORRT_ENGINE_CACHE_ENABLE is 1
* ORT_TENSORRT_DUMP_SUBGRAPHS: Dumps the subgraphs that are transformed into TRT engines in onnx format to the filesystem. This can help debugging subgraphs, e.g. by using `trtexec --onnx my_model.onnx` and check the outputs of the parser.
By default TensorRT execution provider builds an ICudaEngine with max workspace size = 1 GB, max partition iterations = 1000, min subgraph size = 1, FP16 mode is disabled and TensorRT engine caching is disabled.
One can override these defaults by setting environment variables ORT_TENSORRT_MAX_WORKSPACE_SIZE, ORT_TENSORRT_MAX_PARTITION_ITERATIONS, ORT_TENSORRT_MIN_SUBGRAPH_SIZE, ORT_TENSORRT_FP16_ENABLE, ORT_TENSORRT_ENGINE_CACHE_ENABLE and ORT_TENSORRT_ENGINE_CACHE_PATH.