embedl-deploy-tensorrt 0.6.0__tar.gz → 0.6.1__tar.gz

{embedl_deploy_tensorrt-0.6.0 → embedl_deploy_tensorrt-0.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: embedl-deploy-tensorrt
-Version: 0.6.0
+Version: 0.6.1
 Summary: TensorRT backend for embedl-deploy.
 Author-email: Embedl AB <support@embedl.com>
 Project-URL: Homepage, https://www.embedl.com/
@@ -86,10 +86,7 @@ model = Model().eval()
 example_input = torch.randn(1, 3, 224, 224)
 
 # 2. Transform — fuse and optimize for TensorRT in one call
-# For more compatibility you can trace your model with torch.export.export
-# as follows:
-# model = torch.export.export(model, (example_input)).module()
-res = transform(model, patterns=TENSORRT_PATTERNS)
+res = transform(model, (example_input,), patterns=TENSORRT_PATTERNS)
 print("Model\n", res.model.print_readable())
 print("Matches", "\n".join([str(match) for match in res.matches]))
 
@@ -149,7 +146,7 @@ the reference **from the fused graph**, not from the original model:
 ```python
 from embedl_deploy.quantize import quantize, QuantConfig, ModulesToSkip
 
-res = transform(model, patterns=TENSORRT_PATTERNS)
+res = transform(model, (example_input,), patterns=TENSORRT_PATTERNS)
 
 # Grab the conv instance from the fused graph (not from the original model)
 first_conv = res.model.FusedConvBNActMaxPool_0.conv

{embedl_deploy_tensorrt-0.6.0 → embedl_deploy_tensorrt-0.6.1}/README.md

@@ -67,10 +67,7 @@ model = Model().eval()
 example_input = torch.randn(1, 3, 224, 224)
 
 # 2. Transform — fuse and optimize for TensorRT in one call
-# For more compatibility you can trace your model with torch.export.export
-# as follows:
-# model = torch.export.export(model, (example_input)).module()
-res = transform(model, patterns=TENSORRT_PATTERNS)
+res = transform(model, (example_input,), patterns=TENSORRT_PATTERNS)
 print("Model\n", res.model.print_readable())
 print("Matches", "\n".join([str(match) for match in res.matches]))
 
@@ -130,7 +127,7 @@ the reference **from the fused graph**, not from the original model:
 ```python
 from embedl_deploy.quantize import quantize, QuantConfig, ModulesToSkip
 
-res = transform(model, patterns=TENSORRT_PATTERNS)
+res = transform(model, (example_input,), patterns=TENSORRT_PATTERNS)
 
 # Grab the conv instance from the fused graph (not from the original model)
 first_conv = res.model.FusedConvBNActMaxPool_0.conv

{embedl_deploy_tensorrt-0.6.0 → embedl_deploy_tensorrt-0.6.1}/src/embedl_deploy/__init__.py

@@ -8,6 +8,7 @@ from embedl_deploy._internal.core.plan import (
     TransformationResult,
     apply_transformation_plan,
     get_transformation_plan,
+    prepare_graph,
     transform,
 )
 from embedl_deploy.version.public import PUBLIC_VERSION
@@ -21,5 +22,6 @@ __all__ = [
     "__version__",
     "apply_transformation_plan",
     "get_transformation_plan",
+    "prepare_graph",
     "transform",
 ]

{embedl_deploy_tensorrt-0.6.0 → embedl_deploy_tensorrt-0.6.1}/src/embedl_deploy/version/public.py

@@ -2,4 +2,4 @@
 
 """The hardcoded public version of the package."""
 
-PUBLIC_VERSION = '0.6.0'
+PUBLIC_VERSION = '0.6.1'