tkonolige commented on a change in pull request #8793:
URL: https://github.com/apache/tvm/pull/8793#discussion_r692216754
##########
File path: docs/dev/debugger.rst
##########
@@ -123,12 +123,12 @@ Example of loading the parameters
How to use Debugger?
***************************************
-1. In ``config.cmake`` set the ``USE_GRAPH_EXECUTOR_DEBUG`` flag to ``ON``
+1. In ``config.cmake`` set the ``USE_GRAPH_RUNTIME_DEBUG`` flag to ``ON``
::
# Whether enable additional graph debug functions
- set(USE_GRAPH_EXECUTOR_DEBUG ON)
+ set(USE_GRAPH_RUNTIME_DEBUG ON)
Review comment:
`USE_GRAPH_EXECUTOR_DEBUG` and `USE_GRAPH_RUNTIME_DEBUG` are deprecated.
You should use `USE_PROFILER` instead.
##########
File path: docs/dev/debugger.rst
##########
@@ -148,6 +148,22 @@ How to use Debugger?
m.run()
tvm_out = m.get_output(0, tvm.nd.empty(out_shape, dtype)).numpy()
+4. If network previously was exported to external libray using
``lib.export_library("network.so")``
+ like shared object file/dynamic linked library, the initialization
+ of debug runtime will be slightly different
+
+::
+ lib = tvm.runtime.load_module("network.so")
+ m = graph_executor.GraphModuleDebug(lib["debug_create"]("default", dev),
+ [dev], lib["get_json"](),
dump_root="/tmp/tvmdbg")
Review comment:
Does `graph_executor.create` not work here?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
