-
Notifications
You must be signed in to change notification settings - Fork 0
engine compatibility #2
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
base: main
Are you sure you want to change the base?
Conversation
51ef969 to
09b8efb
Compare
09b8efb to
348ff75
Compare
| if(node->OpType() == EPCONTEXT_OP) { | ||
| auto& attrs = node->GetAttributes(); | ||
| auto trt_engine = attrs.at(EP_CACHE_CONTEXT); | ||
| if(!trt::isValidEngine(trt_engine)) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we call TRT API from here? How do we initialize TRT runtime?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
onnxruntime/onnxruntime/core/providers/nv_tensorrt_rtx/nv_execution_provider.cc
Lines 1207 to 1208 in 396fd13
| auto lock = GetApiLock(); | |
| runtime_ = std::unique_ptr<nvinfer1::IRuntime>(nvinfer1::createInferRuntime(GetTensorrtLogger(detailed_build_log_))); |
| * Recompile if not incompatible | ||
| */ | ||
| virtual common::StatusCode isValidCompiledModel(const onnxruntime::Graph& graph) { | ||
| return true; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
you probably wanted to return MODEL_SUPPORTED_OPTIMAL here (or maybe MODEL_UNSUPPORTED)?
pseudo code for compiled model compatibility