saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-25 19:48:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[TensorRT EP] Fix to build ORT on legacy TRT8.5 (#23215)

Browse source 
### Description
<!-- Describe your changes. -->
For legacy jetson users who use jetpack 5.x, the latest TRT version is
8.5.
Add version check to newer trt features to fix build on jetpack 5.x
(cuda11.8+gcc11 are required)


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This commit is contained in:
Yifan Li 2025-01-01 19:24:24 -08:00 committed by GitHub
parent a3833a5e79
commit bc91f5c72e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
View file

@ -3146,12 +3146,14 @@ Status TensorrtExecutionProvider::CreateNodeComputeInfoFromGraph(const GraphView
}
std::string cache_hw_compat = "_sm" + compute_capability_;
#if NV_TENSORRT_MAJOR == 8 && NV_TENSORRT_MINOR > 5 || NV_TENSORRT_MAJOR > 8
// Enable hardware compatility mode if assigned
if (engine_cache_enable_ && engine_hw_compatible_) {
trt_config->setHardwareCompatibilityLevel(nvinfer1::HardwareCompatibilityLevel::kAMPERE_PLUS);
cache_hw_compat = "_sm80+";
LOGS_DEFAULT(VERBOSE) << "[TensorRT EP] Hardware compatibility is enabled when loading and capturing engine cache.";
}
#endif
// Name the engine cache based on GPU compute capacity and reduce the chance of loading an incompatible cache
// Note: Engine cache generated on a GPU with large memory might not be loadable on a GPU with smaller memory, even if they share the same compute capacity
@ -3530,10 +3532,12 @@ Status TensorrtExecutionProvider::CreateNodeComputeInfoFromGraph(const GraphView
// Enable hardware compatility mode if assigned
std::string cache_hw_compat = "_sm" + compute_capability_;
#if NV_TENSORRT_MAJOR == 8 && NV_TENSORRT_MINOR > 5 || NV_TENSORRT_MAJOR > 8
if (engine_cache_enable_ && engine_hw_compatible_) {
cache_hw_compat = "_sm80+";
LOGS_DEFAULT(VERBOSE) << "[TensorRT EP] Hardware compatibility is enabled when loading and capturing engine cache.";
}
#endif
// Name the engine cache based on GPU compute capacity and reduce the chance of loading an incompatible cache
// Note: Engine cache generated on a GPU with large memory might not be loadable on a GPU with smaller memory, even if they share the same compute capacity
@ -3736,11 +3740,13 @@ Status TensorrtExecutionProvider::CreateNodeComputeInfoFromGraph(const GraphView
}
}
#if NV_TENSORRT_MAJOR == 8 && NV_TENSORRT_MINOR > 5 || NV_TENSORRT_MAJOR > 8
// Enable hardware compatility mode if assigned
if (trt_state->engine_hw_compatible) {
trt_config->setHardwareCompatibilityLevel(nvinfer1::HardwareCompatibilityLevel::kAMPERE_PLUS);
LOGS_DEFAULT(INFO) << "[TensorRT EP] Re-generate engine with hardware compatibility enabled.";
}
#endif
// Build engine
std::unique_ptr<nvinfer1::IHostMemory> serialized_engine;