wasi-nn: Support uint8 quantized networks (#2433)

Support (non-full) uint8 quantized networks.
Inputs and outputs are still required to be `float`. The (de)quantization is done internally by wasi-nn.

Example generated from `quantized_model.py`:
![Screenshot from 2023-08-07 17-57-05](https://github.com/bytecodealliance/wasm-micro-runtime/assets/80318361/91f12ff6-870c-427a-b1dc-e307f7d1f5ee)

Visualization with [netron](https://netron.app/).

core/iwasm/libraries/wasi-nn/test/build.sh

@@ -1,6 +1,10 @@
+#!/bin/sh
+
 # Copyright (C) 2019 Intel Corporation.  All rights reserved.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
+CURR_PATH=$(cd $(dirname $0) && pwd -P)
+
 # WASM application that uses WASI-NN
 
 /opt/wasi-sdk/bin/clang \
@@ -13,9 +17,25 @@
 
 # TFLite models to use in the tests
 
-cd models
+cd ${CURR_PATH}/models
 python3 average.py
 python3 max.py
 python3 mult_dimension.py
 python3 mult_outputs.py
 python3 sum.py
+
+# Specific tests for TPU
+
+cd ${CURR_PATH}
+/opt/wasi-sdk/bin/clang \
+    -Wl,--allow-undefined \
+    -Wl,--strip-all,--no-entry \
+    --sysroot=/opt/wasi-sdk/share/wasi-sysroot \
+    -I../include -I../src/utils \
+    -o test_tensorflow_quantized.wasm \
+    test_tensorflow_quantized.c utils.c
+
+cd ${CURR_PATH}/models
+python3 quantized.py
+
+cd ${CURR_PATH}