File tree 1 file changed +8
-1
lines changed
1 file changed +8
-1
lines changed Original file line number Diff line number Diff line change 1
1
<!--
2
- # Copyright 2018-2023 , NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # Copyright 2018-2024 , NVIDIA CORPORATION & AFFILIATES. All rights reserved.
3
3
#
4
4
# Redistribution and use in source and binary forms, with or without
5
5
# modification, are permitted provided that the following conditions
@@ -806,6 +806,13 @@ performance, you can use
806
806
[ Model Analyzer] ( https://github.com/triton-inference-server/model_analyzer )
807
807
to find the optimal model configurations.
808
808
809
+ When crafting the ensemble steps, it is useful to note the distinction between
810
+ * key* and * value* on the ` input_map ` /` output_map ` :
811
+ * * key* : An ` input ` /` output ` tensor name on the composing model.
812
+ * * value* : A tensor name on the ensemble model, which acts as an identifier
813
+ connecting ensemble ` input ` /` output ` to those on the composing model and between
814
+ composing models.
815
+
809
816
#### Additional Resources
810
817
811
818
You can find additional end-to-end ensemble examples in the links below:
You can’t perform that action at this time.
0 commit comments