Fix broken links in md docks (#228)

Author: arashb

docs/build.md

@@ -75,7 +75,7 @@ in the LCE root directory.
 ## Build LCE Runtime
 
 LCE runtime has a diverse platform support, covering
-[Android](/compute-engine/quickstart_android) and [ARM-based boards](/compute-engine/build_arm)
+[Android](https://docs.larq.dev/compute-engine/quickstart_android) and [ARM-based boards](https://docs.larq.dev/compute-engine/build_arm)
 such as Raspberry Pi. To build/install/run LCE runtime on
 each of these platforms, please refer to the corresponding guide.
 

docs/build_arm.md

@@ -19,7 +19,7 @@ the following order:
    [Cross-compiling LCE with Make](#cross-compiling-lce-with-make).
 
 This guide will show you how to build the [LCE example program](https://github.com/larq/compute-engine/blob/master/examples/lce_minimal.cc).
-See [here](/compute-engine/inference) to find out how you can create your own LCE
+See [here](https://docs.larq.dev/compute-engine/inference) to find out how you can create your own LCE
 inference binary.
 
 NOTE: Although the Raspberry Pi 3 and Raspberry Pi 4 have 64-bit CPUs, the
@@ -29,7 +29,7 @@ as [Manjaro](https://manjaro.org/download/#raspberry-pi-4-xfce) should be used.
 
 ## Cross-compiling LCE with Bazel
 
-First configure Bazel using the instructions [here](/compute-engine/build#configure-bazelrc).
+First configure Bazel using the instructions [here](https://docs.larq.dev/compute-engine/build#configure-bazelrc).
 
 To cross-compile the LCE example for ARM architectures, the bazel
 target needs to be built with the `--config=rpi3` (32-bit ARM) or

docs/inference.md

@@ -7,7 +7,7 @@ uses LCE custom operators instead of built-in TensorFlow Lite operators for each
 subgraph of the model.
 
 This guide describes how to create a TensorFlow Lite interpreter with registered
-LCE custom Ops and perform an inference with a [converted Larq model](/compute-engine/converter)
+LCE custom Ops and perform an inference with a [converted Larq model](https://docs.larq.dev/compute-engine/converter)
 using LCE C++ API.
 
 ## Load and run a model in C++

docs/quickstart_android.md

@@ -6,11 +6,11 @@ you must have the [Android NDK](https://developer.android.com/ndk) and
 Below we explain how to install the Android prerequisites in the LCE
 Docker container and how to configure the LCE Bazel build settings
 accordingly. Before proceeding with the next steps, please follow
-the instructions in the main [LCE build guide](/compute-engine/build) to setup the
+the instructions in the main [LCE build guide](https://docs.larq.dev/compute-engine/build) to setup the
 Docker container for LCE and the Bazel build system.
 
 NOTE: we recommend using the docker volume as described in the
-[LCE build guide](/compute-engine/build) to be able to easily transfer
+[LCE build guide](https://docs.larq.dev/compute-engine/build) to be able to easily transfer
 files in-between the container and host machine.
 
 #### Install prerequisites
@@ -47,7 +47,7 @@ build --action_env ANDROID_SDK_HOME="/usr/local/android/android-sdk-linux"
 
 #### Build an LCE inference binary
 
-To build an LCE inference binary for Android (see [here](/compute-engine/inference) for creating your
+To build an LCE inference binary for Android (see [here](https://docs.larq.dev/compute-engine/inference) for creating your
 own LCE binary) the Bazel target needs to build with `--config=android_arm64` flag.
 
 To build the [minimal example](https://github.com/larq/compute-engine/blob/master/examples/lce_minimal.cc) for Android,
@@ -70,7 +70,7 @@ See below on how to copy them to your android device.
 
 #### Run inference
 
-To run the inference with a [Larq converted model](/compute-engine/converter) on an android phone,
+To run the inference with a [Larq converted model](https://docs.larq.dev/compute-engine/converter) on an android phone,
 please follow these steps on your host machine (replace the `lce_benchmark_model` with your
 desired inference binary):