Mousius commented on a change in pull request #8023:
URL: https://github.com/apache/tvm/pull/8023#discussion_r644207926
##########
File path: include/tvm/runtime/module.h
##########
@@ -232,6 +232,8 @@ constexpr const char* tvm_param_prefix = "__tvm_param__";
constexpr const char* tvm_lookup_linked_param = "_lookup_linked_param";
/*! \brief The main AOT executor function */
constexpr const char* tvm_run_func_prefix = "tvm__run_func";
+/*! \brief The entrypoint function to the generated network */
Review comment:
Sorry, what I meant was that the code to name mangle and allow multiple
models is landing in #8014; that means we should use `tvm_module_main` here for
now and it'll be replaced shortly by one with the model name included - thus
providing the outcome we're looking for?
Also, I believe we'll see multiple models in a single embedded application
with increasing frequency and we can't leave out this use case.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
