diff --git a/README.md b/README.md
index 64c15c4fb..3128e2b29 100644
--- a/README.md
+++ b/README.md
@@ -182,7 +182,11 @@ releases! 🌟
 
    ```bash
    $ cd ragflow/docker
+   # Use CPU for embedding and DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
diff --git a/README_id.md b/README_id.md
index 67dd103f9..d920052d2 100644
--- a/README_id.md
+++ b/README_id.md
@@ -175,7 +175,11 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 
    ```bash
    $ cd ragflow/docker
+   # Use CPU for embedding and DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
diff --git a/README_ja.md b/README_ja.md
index 0853285e2..4bbb82bc0 100644
--- a/README_ja.md
+++ b/README_ja.md
@@ -155,7 +155,11 @@
 
    ```bash
    $ cd ragflow/docker
+   # Use CPU for embedding and DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
diff --git a/README_ko.md b/README_ko.md
index f99394cf4..05da534a2 100644
--- a/README_ko.md
+++ b/README_ko.md
@@ -156,7 +156,11 @@
 
    ```bash
    $ cd ragflow/docker
+   # Use CPU for embedding and DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
diff --git a/README_pt_br.md b/README_pt_br.md
index 1647f8e26..874bd5d37 100644
--- a/README_pt_br.md
+++ b/README_pt_br.md
@@ -175,7 +175,11 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 
     ```bash
     $ cd ragflow/docker
+    # Use CPU for embedding and DeepDoc tasks:
     $ docker compose -f docker-compose.yml up -d
+    
+    # To use GPU to accelerate embedding and DeepDoc tasks:
+    # docker compose -f docker-compose-gpu.yml up -d
     ```
 
     | Tag da imagem RAGFlow | Tamanho da imagem (GB) | Possui modelos de incorporação? | Estável?                 |
diff --git a/README_tzh.md b/README_tzh.md
index 097ac6cef..fcedea901 100644
--- a/README_tzh.md
+++ b/README_tzh.md
@@ -154,7 +154,11 @@
 
    ```bash
    $ cd ragflow/docker
+   # Use CPU for embedding and DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
diff --git a/README_zh.md b/README_zh.md
index bbe32b666..a4c5e7d15 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -155,7 +155,11 @@
 
    ```bash
    $ cd ragflow/docker
+   # Use CPU for embedding and DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx
index e00b3af59..ce274eb76 100644
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -189,7 +189,11 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
    :::
 
    ```bash
+   # Use CPU for embedding and DeepDoc tasks:
    $ docker compose -f docker-compose.yml up -d
+
+   # To use GPU to accelerate embedding and DeepDoc tasks:
+   # docker compose -f docker-compose-gpu.yml up -d
    ```
 
 ```mdx-code-block