push

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.engine filter=lfs diff=lfs merge=lfs -text

metadata.json

@@ -0,0 +1 @@
+{"class_name": "PytorchONNXTensorRTInferenceLearner", "module_name": "nebullvm.operations.inference_learners.tensor_rt", "network_parameters": {"batch_size": 10, "input_infos": [{"dtype": "float16", "size": [10, 4, 64, 64]}, {"dtype": "int64", "size": [1]}, {"dtype": "float16", "size": [10, 77, 768]}], "output_sizes": [[10, 4, 64, 64]], "output_types": ["float16"], "dynamic_info": {"inputs": [{"0": {"name": "2B", "min_val": 10, "opt_val": 10, "max_val": 10}, "2": {"name": "H", "min_val": 64, "opt_val": 64, "max_val": 64}, "3": {"name": "W", "min_val": 64, "opt_val": 64, "max_val": 64}}, {}, {"0": {"name": "2B", "min_val": 10, "opt_val": 10, "max_val": 10}}], "outputs": [{"0": "2B", "2": "H", "3": "W"}]}}, "input_tfms": {"tfms": [{"module": "nebullvm.tools.transformations", "name": "VerifyContiguity"}]}, "device": "gpu", "input_names": ["input_0", "input_1", "input_2"], "output_names": ["output_0"]}

tensor_rt.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0f9ecf67b8042791c6b0d70cc9b7fe948e2b56eaf9a362a5dd5f375ffcb9c9
+size 1730902060