saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-31 23:27:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix url in the code documentation (graph optimizations) (#16770)

Browse source 
### Description
Fix a wrong url in the documentation as mentioned in issue #16678.



### Motivation and Context
Better documentation.
This commit is contained in:
Xavier Dupré 2023-07-20 16:02:22 +02:00 committed by GitHub
parent c314d7724f
commit 2bc9fbb621
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
include/onnxruntime/core/session/onnxruntime_c_api.h
View file

@ -987,7 +987,7 @@ struct OrtApi {
/** \brief Set the optimization level to apply when loading a graph
*
* Please see https://onnxruntime.ai/docs/performance/graph-optimizations.html for an in-depth explanation
* Please see https://onnxruntime.ai/docs/performance/model-optimizations/graph-optimizations.html for an in-depth explanation
* \param[in,out] options The session options object
* \param[in] graph_optimization_level The optimization level
*

2
objectivec/include/ort_enums.h
View file

@ -43,7 +43,7 @@ typedef NS_ENUM(int32_t, ORTTensorElementDataType) {
/**
* The ORT graph optimization levels.
* See here for more details:
* https://onnxruntime.ai/docs/performance/graph-optimizations.html
* https://onnxruntime.ai/docs/performance/model-optimizations/graph-optimizations.html
*/
typedef NS_ENUM(int32_t, ORTGraphOptimizationLevel) {
ORTGraphOptimizationLevelNone,

2
onnxruntime/python/tools/transformers/optimizer.py
View file

@ -207,7 +207,7 @@ def optimize_model(
):
"""Optimize Model by OnnxRuntime and/or python fusion logic.
ONNX Runtime has graph optimizations (https://onnxruntime.ai/docs/performance/graph-optimizations.html).
ONNX Runtime has graph optimizations (https://onnxruntime.ai/docs/performance/model-optimizations/graph-optimizations.html).
However, the coverage is limited. We also have graph fusions that implemented in Python to improve the coverage.
They can combined: ONNX Runtime will run first when opt_level > 0, then graph fusions in Python will be applied.

2
tools/python/util/optimize_onnx_model.py
View file

@ -14,7 +14,7 @@ def optimize_model_helper():
f"{os.path.basename(__file__)}:{optimize_model_helper.__name__}",
description="""
Optimize an ONNX model using ONNX Runtime to the specified level.
See https://onnxruntime.ai/docs/performance/graph-optimizations.html for more
See https://onnxruntime.ai/docs/performance/model-optimizations/graph-optimizations.html for more
details of the optimization levels.""",
)