[docs] [llm] [template] update ray version + use anyscale image for the gpt-oss deployment

doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/Dockerfile

@@ -1,8 +1,8 @@
-FROM anyscale/ray:2.49.0-slim-py312-cu128
+FROM anyscale/ray:2.52.0-slim-py312-cu128
 
 # C compiler for Triton’s runtime build step (vLLM V1 engine)
 # https://github.com/vllm-project/vllm/issues/2997
 RUN sudo apt-get update && \
     sudo apt-get install -y --no-install-recommends build-essential
 
-RUN pip install vllm==0.10.1
+RUN pip install vllm==0.11.0

doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md

@@ -200,33 +200,21 @@ For production deployment, use Anyscale services to deploy the Ray Serve app to
 
 ### Launch the service
 
-Anyscale provides out-of-the-box images (`anyscale/ray-llm`), which come pre-loaded with Ray Serve LLM, vLLM, and all required GPU and runtime dependencies. See the [Anyscale base images](https://docs.anyscale.com/reference/base-images) for details on what each image includes.
+Anyscale provides out-of-the-box images (`anyscale/ray-llm`) which come pre-loaded with Ray Serve LLM, vLLM, and all required GPU/runtime dependencies. This makes it easy to get started without building a custom image.
 
-Build a minimal Dockerfile:
-```Dockerfile
-FROM anyscale/ray:2.49.0-slim-py312-cu128
-
-# C compiler for Triton’s runtime build step (vLLM V1 engine)
-# https://github.com/vllm-project/vllm/issues/2997
-RUN sudo apt-get update && \
-    sudo apt-get install -y --no-install-recommends build-essential
-
-RUN pip install vllm==0.10.1
-```
-
-Create your Anyscale service configuration in a new `service.yaml` file and reference the Dockerfile with `containerfile`:
+Create your Anyscale Service configuration in a new `service.yaml` file:
 
 ```yaml
 # service.yaml
-name: deploy-gpt-oss
-containerfile: ./Dockerfile # Build Ray Serve LLM with vllm==0.10.1
+name: deploy-llama-3-8b
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
 working_dir: .
 cloud:
 applications:
   # Point to your app in your Python module
-  - import_path: serve_gpt_oss:app
+  - import_path: serve_llama_3_1_8b:app
 ```
 
 
@@ -237,6 +225,19 @@ Deploy your service:
 anyscale service deploy -f service.yaml
 ```
 
+**Custom Dockerfile**  
+You can customize the container by building your own Dockerfile. In your Anyscale Service config, reference the Dockerfile with `containerfile` (instead of `image_uri`):
+
+```yaml
+# service.yaml
+# Replace:
+# image_uri: anyscale/ray-llm:2.49.0-py311-cu128
+
+# with:
+containerfile: ./Dockerfile
+```
+
+See the [Anyscale base images](https://docs.anyscale.com/reference/base-images) for details on what each image includes.
 
 ---
 

doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb

@@ -263,33 +263,21 @@
     "\n",
     "### Launch the service\n",
     "\n",
-    "Anyscale provides out-of-the-box images (`anyscale/ray-llm`), which come pre-loaded with Ray Serve LLM, vLLM, and all required GPU and runtime dependencies. See the [Anyscale base images](https://docs.anyscale.com/reference/base-images) for details on what each image includes.\n",
+    "Anyscale provides out-of-the-box images (`anyscale/ray-llm`) which come pre-loaded with Ray Serve LLM, vLLM, and all required GPU/runtime dependencies. This makes it easy to get started without building a custom image.\n",
     "\n",
-    "Build a minimal Dockerfile:\n",
-    "```Dockerfile\n",
-    "FROM anyscale/ray:2.49.0-slim-py312-cu128\n",
-    "\n",
-    "# C compiler for Triton’s runtime build step (vLLM V1 engine)\n",
-    "# https://github.com/vllm-project/vllm/issues/2997\n",
-    "RUN sudo apt-get update && \\\n",
-    "    sudo apt-get install -y --no-install-recommends build-essential\n",
-    "\n",
-    "RUN pip install vllm==0.10.1\n",
-    "```\n",
-    "\n",
-    "Create your Anyscale service configuration in a new `service.yaml` file and reference the Dockerfile with `containerfile`:\n",
+    "Create your Anyscale Service configuration in a new `service.yaml` file:\n",
     "\n",
     "```yaml\n",
     "# service.yaml\n",
-    "name: deploy-gpt-oss\n",
-    "containerfile: ./Dockerfile # Build Ray Serve LLM with vllm==0.10.1\n",
+    "name: deploy-llama-3-8b\n",
+    "image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.\n",
     "compute_config:\n",
     "  auto_select_worker_config: true \n",
     "working_dir: .\n",
     "cloud:\n",
     "applications:\n",
     "  # Point to your app in your Python module\n",
-    "  - import_path: serve_gpt_oss:app\n",
+    "  - import_path: serve_llama_3_1_8b:app\n",
     "```\n",
     "\n",
     "\n",
@@ -311,6 +299,19 @@
    "id": "7e6de36c",
    "metadata": {},
    "source": [
+    "**Custom Dockerfile**  \n",
+    "You can customize the container by building your own Dockerfile. In your Anyscale Service config, reference the Dockerfile with `containerfile` (instead of `image_uri`):\n",
+    "\n",
+    "```yaml\n",
+    "# service.yaml\n",
+    "# Replace:\n",
+    "# image_uri: anyscale/ray-llm:2.49.0-py311-cu128\n",
+    "\n",
+    "# with:\n",
+    "containerfile: ./Dockerfile\n",
+    "```\n",
+    "\n",
+    "See the [Anyscale base images](https://docs.anyscale.com/reference/base-images) for details on what each image includes.\n",
     "\n",
     "---\n",
     "\n",

doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml

@@ -1,6 +1,6 @@
 # service.yaml
 name: deploy-gpt-oss
-containerfile: ./Dockerfile # Build Ray Serve LLM with vllm==0.10.1
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
 working_dir: .

doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/Dockerfile

@@ -1,8 +1,8 @@
-FROM anyscale/ray:2.49.0-slim-py312-cu128
+FROM anyscale/ray:2.52.0-slim-py312-cu128
 
 # C compiler for Triton’s runtime build step (vLLM V1 engine)
 # https://github.com/vllm-project/vllm/issues/2997
 RUN sudo apt-get update && \
     sudo apt-get install -y --no-install-recommends build-essential
 
-RUN pip install vllm==0.10.0
+RUN pip install vllm==0.11.0

doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/README.md

@@ -190,7 +190,7 @@ Create your Anyscale service configuration in a new `service.yaml` file:
 ```yaml
 #service.yaml
 name: deploy-deepseek-r1
-image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
   # Change default disk size to 1000GB

doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/notebook.ipynb

@@ -241,7 +241,7 @@
     "```yaml\n",
     "#service.yaml\n",
     "name: deploy-deepseek-r1\n",
-    "image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.\n",
+    "image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.\n",
     "compute_config:\n",
     "  auto_select_worker_config: true \n",
     "  # Change default disk size to 1000GB\n",

doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/service.yaml

@@ -1,6 +1,6 @@
 #service.yaml
 name: deploy-deepseek-r1
-image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
   # Change default disk size to 1000GB

doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/Dockerfile

@@ -1,8 +1,8 @@
-FROM anyscale/ray:2.49.0-slim-py312-cu128
+FROM anyscale/ray:2.52.0-slim-py312-cu128
 
 # C compiler for Triton’s runtime build step (vLLM V1 engine)
 # https://github.com/vllm-project/vllm/issues/2997
 RUN sudo apt-get update && \
     sudo apt-get install -y --no-install-recommends build-essential
 
-RUN pip install vllm==0.10.0
+RUN pip install vllm==0.11.0

doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/README.md

@@ -167,7 +167,7 @@ Create your Anyscale service configuration in a new `service.yaml` file:
 ```yaml
 # service.yaml
 name: deploy-llama-3-70b
-image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
 working_dir: .

doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/notebook.ipynb

@@ -218,7 +218,7 @@
     "```yaml\n",
     "# service.yaml\n",
     "name: deploy-llama-3-70b\n",
-    "image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.\n",
+    "image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.\n",
     "compute_config:\n",
     "  auto_select_worker_config: true \n",
     "working_dir: .\n",

doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/service.yaml

@@ -1,6 +1,6 @@
 # service.yaml
 name: deploy-llama-3-70b
-image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
 working_dir: .

doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/Dockerfile

@@ -1,8 +1,8 @@
-FROM anyscale/ray:2.49.0-slim-py312-cu128
+FROM anyscale/ray:2.52.0-slim-py312-cu128
 
 # C compiler for Triton’s runtime build step (vLLM V1 engine)
 # https://github.com/vllm-project/vllm/issues/2997
 RUN sudo apt-get update && \
     sudo apt-get install -y --no-install-recommends build-essential
 
-RUN pip install vllm==0.10.0
+RUN pip install vllm==0.11.0

doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/README.md

@@ -163,7 +163,7 @@ Create your Anyscale Service configuration in a new `service.yaml` file:
 ```yaml
 # service.yaml
 name: deploy-llama-3-8b
-image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
 working_dir: .

doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/notebook.ipynb

@@ -214,7 +214,7 @@
     "```yaml\n",
     "# service.yaml\n",
     "name: deploy-llama-3-8b\n",
-    "image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.\n",
+    "image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.\n",
     "compute_config:\n",
     "  auto_select_worker_config: true \n",
     "working_dir: .\n",

doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/service.yaml

@@ -1,6 +1,6 @@
 # service.yaml
 name: deploy-llama-3-8b
-image_uri: anyscale/ray-llm:2.49.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
+image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. Use `containerfile: ./Dockerfile` to use a custom Dockerfile.
 compute_config:
   auto_select_worker_config: true 
 working_dir: .