Pick up predtuner updates and updated related document

hpvm/docs/components/index.rst

@@ -33,7 +33,7 @@ which explains their role, usage, and other details.
    keras-support
    keras-benchmarks
    torch2hpvm
-   predtuner
+   Predictive Tuner<https://predtuner.readthedocs.io/en/latest/index.html>
    hpvm-profiler
 
 

hpvm/docs/components/predtuner.rst

-../../projects/predtuner/README.rst
\ No newline at end of file

hpvm/docs/getting-started.rst

@@ -188,7 +188,7 @@ After the tuning finishes, the tuner will
 * save the HPVM config format (write-only) at ``./hpvm_confs.txt``.
 
 It is also possible to save the configuration in other formats
-(see the :doc:`predtuner documentation </components/predtuner>`).
+(see the `predtuner documentation <https://predtuner.readthedocs.io/en/latest/index.html>`_).
 
 Profiling the Configurations
 ----------------------------

predtuner @ d0517903

-Subproject commit 7159825f27ee7b3c5731ee1b9418c6eafda6622a
+Subproject commit d051790317d29a59ca15541d20c1a61318e56932

hpvm/test/dnn_benchmarks/pytorch/test_tuning/test_tuning.py

@@ -24,14 +24,14 @@ def main():
     binary_file, exporter = dnn.export_example_dnn(netname, codegen_dir, True)
     metadata_file = codegen_dir / exporter.metadata_file_name
     # Tuning
-    app = PipedBinaryApp("test", binary_file, metadata_file, tuning_device="cpu")
+    app = PipedBinaryApp("test", binary_file, metadata_file, target_device="cpu")
     tuner = app.get_tuner()
     tuner.tune(
         5,
         3.0,
         is_threshold_relative=True,
         cost_model="cost_linear",
-        qos_model="qos_p1" if is_pred else "none",
+        qos_model="qos_p1" if is_pred else None,
     )
     tuner.dump_configs("configs.json")
     fig = tuner.plot_configs(show_qos_loss=True)