[TVMC] Keep quantized weights when importing PyTorch model (apache#9417)

BYOC requires `keep_quantized_weight` be set to true when converting PyTorch models using `from_torch`. Setting this to be True when using TVMC. Change-Id: I8c183f9f802ea54d24679a4017e56481d84e5655
mehrdadh · Dec 1, 2021 · 0adf6e6 · 0adf6e6
1 parent 5d57ab7
commit 0adf6e6
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/python/tvm/driver/tvmc/frontends.py b/python/tvm/driver/tvmc/frontends.py
@@ -262,7 +262,9 @@ def load(self, path, shape_dict=None, **kwargs):
         input_shapes = list(shape_dict.items())
 
         logger.debug("parse Torch model and convert into Relay computation graph")
-        return relay.frontend.from_pytorch(traced_model, input_shapes, **kwargs)
+        return relay.frontend.from_pytorch(
+            traced_model, input_shapes, keep_quantized_weight=True, **kwargs
+        )
 
 
 class PaddleFrontend(Frontend):