As GraphRuntime does not provide control-flow logics, we have to split our model to two parts. While we need to share parameters between them to save memory usage. Solution: 1) add "lazy_init_input" in graph's attributes "attrs": { ... ... "lazy_init_input": [ "list_str", [ "p0" ] ] } 2) allow un-allocated NDArray entry in SetupStorage 3) utilize "set_input_zero_copy" function to set parameters
Name |
Last commit
|
Last update |
---|---|---|
.. | ||
api | Loading commit data... | |
arithmetic | Loading commit data... | |
autotvm | Loading commit data... | |
codegen | Loading commit data... | |
common | Loading commit data... | |
contrib | Loading commit data... | |
lang | Loading commit data... | |
node | Loading commit data... | |
op | Loading commit data... | |
pass | Loading commit data... | |
relay | Loading commit data... | |
runtime | Loading commit data... | |
schedule | Loading commit data... | |
README.md | Loading commit data... |