wasi-nn: Support multiple TFLite models (#2002)
Remove restrictions:
- Only 1 WASM app at a time
- Only 1 model at a time
- `graph` and `graph-execution-context` are ignored
Refer to previous document:
e8d718096d/core/iwasm/libraries/wasi-nn/README.md
This commit is contained in:
@ -19,12 +19,6 @@ To run the tests we assume that the current directory is the root of the reposit
|
||||
|
||||
### Build the runtime
|
||||
|
||||
Build the runtime base image,
|
||||
|
||||
```
|
||||
docker build -t wasi-nn-base -f core/iwasm/libraries/wasi-nn/test/Dockerfile.base .
|
||||
```
|
||||
|
||||
Build the runtime image for your execution target type.
|
||||
|
||||
`EXECUTION_TYPE` can be:
|
||||
@ -84,9 +78,6 @@ Requirements:
|
||||
|
||||
Supported:
|
||||
|
||||
* Only 1 WASM app at a time.
|
||||
* Only 1 model at a time.
|
||||
* `graph` and `graph-execution-context` are ignored.
|
||||
* Graph encoding: `tensorflowlite`.
|
||||
* Execution target: `cpu` and `gpu`.
|
||||
* Tensor type: `fp32`.
|
||||
|
||||
Reference in New Issue
Block a user