diff --git a/docker/docker-compose.dev.yml b/docker/docker-compose.dev.yml
index 5da5bd3f91..3895fa126d 100644
--- a/docker/docker-compose.dev.yml
+++ b/docker/docker-compose.dev.yml
@@ -85,12 +85,12 @@ services:
     image: immich-machine-learning-dev:latest
     # extends:
     #   file: hwaccel.ml.yml
-    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference
+    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl, rknn] for accelerated inference
     build:
       context: ../machine-learning
       dockerfile: Dockerfile
       args:
-        - DEVICE=cpu # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference
+        - DEVICE=cpu # set to one of [armnn, cuda, openvino, openvino-wsl, rknn] for accelerated inference
     ports:
       - 3003:3003
     volumes:
diff --git a/docker/docker-compose.prod.yml b/docker/docker-compose.prod.yml
index 8521390079..561cef75db 100644
--- a/docker/docker-compose.prod.yml
+++ b/docker/docker-compose.prod.yml
@@ -29,12 +29,12 @@ services:
     image: immich-machine-learning:latest
     # extends:
     #   file: hwaccel.ml.yml
-    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference
+    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl, rknn] for accelerated inference
     build:
       context: ../machine-learning
       dockerfile: Dockerfile
       args:
-        - DEVICE=cpu # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference
+        - DEVICE=cpu # set to one of [armnn, cuda, openvino, openvino-wsl, rknn] for accelerated inference
     ports:
       - 3003:3003
     volumes:
@@ -68,22 +68,12 @@ services:
       - 5432:5432
     healthcheck:
       test: >-
-        pg_isready --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" || exit 1;
-        Chksum="$$(psql --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" --tuples-only --no-align
-        --command='SELECT COALESCE(SUM(checksum_failures), 0) FROM pg_stat_database')";
-        echo "checksum failure count is $$Chksum";
-        [ "$$Chksum" = '0' ] || exit 1
+        pg_isready --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" || exit 1; Chksum="$$(psql --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" --tuples-only --no-align --command='SELECT COALESCE(SUM(checksum_failures), 0) FROM pg_stat_database')"; echo "checksum failure count is $$Chksum"; [ "$$Chksum" = '0' ] || exit 1
       interval: 5m
       start_interval: 30s
       start_period: 5m
     command: >-
-      postgres
-      -c shared_preload_libraries=vectors.so
-      -c 'search_path="$$user", public, vectors'
-      -c logging_collector=on
-      -c max_wal_size=2GB
-      -c shared_buffers=512MB
-      -c wal_compression=on
+      postgres -c shared_preload_libraries=vectors.so -c 'search_path="$$user", public, vectors' -c logging_collector=on -c max_wal_size=2GB -c shared_buffers=512MB -c wal_compression=on
     restart: always
 
   # set IMMICH_TELEMETRY_INCLUDE=all in .env to enable metrics
@@ -100,7 +90,7 @@ services:
   # add data source for http://immich-prometheus:9090 to get started
   immich-grafana:
     container_name: immich_grafana
-    command: ['./run.sh', '-disable-reporting']
+    command: [ './run.sh', '-disable-reporting' ]
     ports:
       - 3000:3000
     image: grafana/grafana:11.4.0-ubuntu@sha256:afccec22ba0e4815cca1d2bf3836e414322390dc78d77f1851976ffa8d61051c
diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
index 4b8453ce58..663816f4e3 100644
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@@ -32,12 +32,12 @@ services:
 
   immich-machine-learning:
     container_name: immich_machine_learning
-    # For hardware acceleration, add one of -[armnn, cuda, openvino] to the image tag.
+    # For hardware acceleration, add one of -[armnn, cuda, openvino, rknn] to the image tag.
     # Example tag: ${IMMICH_VERSION:-release}-cuda
     image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}
     # extends: # uncomment this section for hardware acceleration - see https://immich.app/docs/features/ml-hardware-acceleration
     #   file: hwaccel.ml.yml
-    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference - use the `-wsl` version for WSL2 where applicable
+    #   service: cpu # set to one of [armnn, cuda, openvino, openvino-wsl, rknn] for accelerated inference - use the `-wsl` version for WSL2 where applicable
     volumes:
       - model-cache:/cache
     env_file:
@@ -66,22 +66,12 @@ services:
       - ${DB_DATA_LOCATION}:/var/lib/postgresql/data
     healthcheck:
       test: >-
-        pg_isready --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" || exit 1;
-        Chksum="$$(psql --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" --tuples-only --no-align
-        --command='SELECT COALESCE(SUM(checksum_failures), 0) FROM pg_stat_database')";
-        echo "checksum failure count is $$Chksum";
-        [ "$$Chksum" = '0' ] || exit 1
+        pg_isready --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" || exit 1; Chksum="$$(psql --dbname="$${POSTGRES_DB}" --username="$${POSTGRES_USER}" --tuples-only --no-align --command='SELECT COALESCE(SUM(checksum_failures), 0) FROM pg_stat_database')"; echo "checksum failure count is $$Chksum"; [ "$$Chksum" = '0' ] || exit 1
       interval: 5m
       start_interval: 30s
       start_period: 5m
     command: >-
-      postgres
-      -c shared_preload_libraries=vectors.so
-      -c 'search_path="$$user", public, vectors'
-      -c logging_collector=on
-      -c max_wal_size=2GB
-      -c shared_buffers=512MB
-      -c wal_compression=on
+      postgres -c shared_preload_libraries=vectors.so -c 'search_path="$$user", public, vectors' -c logging_collector=on -c max_wal_size=2GB -c shared_buffers=512MB -c wal_compression=on
     restart: always
 
 volumes:
diff --git a/docker/hwaccel.ml.yml b/docker/hwaccel.ml.yml
index d9455d2bb7..41ebc99784 100644
--- a/docker/hwaccel.ml.yml
+++ b/docker/hwaccel.ml.yml
@@ -13,6 +13,18 @@ services:
     volumes:
       - /lib/firmware/mali_csffw.bin:/lib/firmware/mali_csffw.bin:ro # Mali firmware for your chipset (not always required depending on the driver)
       - /usr/lib/libmali.so:/usr/lib/libmali.so:ro # Mali driver for your chipset (always required)
+  
+  rknn:
+    security_opt:
+      - systempaths=unconfined
+      - apparmor=unconfined
+    devices:
+      - /dev/rga:/dev/rga
+      - /dev/dri:/dev/dri
+      - /dev/dma_heap:/dev/dma_heap
+      - /dev/mpp_service:/dev/mpp_service
+    volumes:
+      - /sys/kernel/debug/:/sys/kernel/debug/:ro
 
   cpu: {}
 
diff --git a/docs/docs/features/ml-hardware-acceleration.md b/docs/docs/features/ml-hardware-acceleration.md
index 838b0abccc..0984aaeb5c 100644
--- a/docs/docs/features/ml-hardware-acceleration.md
+++ b/docs/docs/features/ml-hardware-acceleration.md
@@ -10,9 +10,9 @@ You do not need to redo any machine learning jobs after enabling hardware accele
 ## Supported Backends
 
 - ARM NN (Mali)
-- RKNN (Rockchip)
 - CUDA (NVIDIA GPUs with [compute capability](https://developer.nvidia.com/cuda-gpus) 5.2 or higher)
 - OpenVINO (Intel discrete GPUs such as Iris Xe and Arc)
+- RKNN (Rockchip)
 
 ## Limitations
 
@@ -35,15 +35,6 @@ You do not need to redo any machine learning jobs after enabling hardware accele
   - The `hwaccel.ml.yml` file assumes an additional file `/lib/firmware/mali_csffw.bin`, so update accordingly if your device's driver does not require this file
 - Optional: Configure your `.env` file, see [environment variables](/docs/install/environment-variables) for ARM NN specific settings
 
-#### RKNN
-
-- You must have a supported Rockchip SoC, only RK3566 and RK3588 are supported at this moment.
-- Make sure you have the appropriate linux kernel driver installed
-  - This is usually pre-installed on the device vendor's Linux images
-- RKNPU driver V0.9.8 or later must be available in the host server
-  - You may confirm this by running `cat /sys/kernel/debug/rknpu/version` to check the version
-- Optional: Configure your `.env` file, see [environment variables](/docs/install/environment-variables) for RKNN specific settings
-
 #### CUDA
 
 - The GPU must have compute capability 5.2 or greater.
@@ -56,6 +47,14 @@ You do not need to redo any machine learning jobs after enabling hardware accele
 - The server must have a discrete GPU, i.e. Iris Xe or Arc. Expect issues when attempting to use integrated graphics.
 - Ensure the server's kernel version is new enough to use the device for hardware accceleration.
 
+#### RKNN
+
+- You must have a supported Rockchip SoC, only RK3566 and RK3588 are supported at this moment.
+- Make sure you have the appropriate linux kernel driver installed
+  - This is usually pre-installed on the device vendor's Linux images
+- RKNPU driver V0.9.8 or later must be available in the host server
+  - You may confirm this by running `cat /sys/kernel/debug/rknpu/version` to check the version
+- Optional: Configure your `.env` file, see [environment variables](/docs/install/environment-variables) for RKNN specific settings
 ## Setup
 
 1. If you do not already have it, download the latest [`hwaccel.ml.yml`][hw-file] file and ensure it's in the same folder as the `docker-compose.yml`.