From a81b3bb374f2c931e5a1c9c477453806e751426a Mon Sep 17 00:00:00 2001 From: Aydin Abiar Date: Tue, 2 Dec 2025 17:15:33 -0800 Subject: [PATCH 1/5] update ray version + make gpt oss anyscale service deployment use an image instaed of dockerfile Signed-off-by: Aydin Abiar --- .../deployment-serve-llm/gpt-oss/Dockerfile | 4 +-- .../deployment-serve-llm/gpt-oss/README.md | 35 ++++++++++--------- .../gpt-oss/notebook.ipynb | 35 ++++++++++--------- .../deployment-serve-llm/gpt-oss/service.yaml | 2 +- .../large-size-llm/Dockerfile | 4 +-- .../large-size-llm/README.md | 2 +- .../large-size-llm/notebook.ipynb | 2 +- .../large-size-llm/service.yaml | 2 +- .../medium-size-llm/Dockerfile | 4 +-- .../medium-size-llm/README.md | 2 +- .../medium-size-llm/notebook.ipynb | 2 +- .../medium-size-llm/service.yaml | 2 +- .../small-size-llm/Dockerfile | 4 +-- .../small-size-llm/README.md | 2 +- .../small-size-llm/notebook.ipynb | 2 +- .../small-size-llm/service.yaml | 2 +- 16 files changed, 54 insertions(+), 52 deletions(-) diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/Dockerfile b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/Dockerfile index cb8e884572c0..18756083c0a0 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/Dockerfile +++ b/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 \ No newline at end of file +RUN pip install vllm==0.11.0 \ No newline at end of file diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md index 90105c9e6bb5..cd6e63a9b6ae 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md +++ b/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. --- diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb index 67a2d95c5a84..0afe561d6542 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb +++ b/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", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml index 5e6be0427f11..e22a2087efc4 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml +++ b/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: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/Dockerfile b/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/Dockerfile index a2412390df61..18756083c0a0 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/Dockerfile +++ b/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 \ No newline at end of file +RUN pip install vllm==0.11.0 \ No newline at end of file diff --git a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/README.md b/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/README.md index 61557ab44be1..6f327451cb44 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/README.md +++ b/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 diff --git a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/notebook.ipynb index e03c02b97204..a07e660c3462 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/notebook.ipynb +++ b/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", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/service.yaml index 9fb4e4e7130b..5c43377cc564 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/service.yaml +++ b/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 diff --git a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/Dockerfile b/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/Dockerfile index a2412390df61..18756083c0a0 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/Dockerfile +++ b/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 \ No newline at end of file +RUN pip install vllm==0.11.0 \ No newline at end of file diff --git a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/README.md b/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/README.md index 6bdd151e0f8b..d49bb1167cfd 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/README.md +++ b/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: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/notebook.ipynb index f63015fef80f..037e57448f72 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/notebook.ipynb +++ b/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", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/service.yaml index 35388c72f961..f8a08a95418c 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/service.yaml +++ b/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: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/Dockerfile b/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/Dockerfile index a2412390df61..18756083c0a0 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/Dockerfile +++ b/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 \ No newline at end of file +RUN pip install vllm==0.11.0 \ No newline at end of file diff --git a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/README.md b/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/README.md index e0e7e4b5594b..fa9d39c91535 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/README.md +++ b/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: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/notebook.ipynb index 2ca1fbedee84..010c16d3f139 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/notebook.ipynb +++ b/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", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/service.yaml index 4c12e613c0d0..a3e0f3dbc123 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/service.yaml +++ b/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: . From 48cc4220a44d65f7ae98dfaa4c8b109d5a7654e5 Mon Sep 17 00:00:00 2001 From: Aydin Abiar <62435714+Aydin-ab@users.noreply.github.com> Date: Tue, 2 Dec 2025 22:27:41 -0800 Subject: [PATCH 2/5] Apply suggestions from code review Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Aydin Abiar <62435714+Aydin-ab@users.noreply.github.com> --- .../serve/tutorials/deployment-serve-llm/gpt-oss/README.md | 2 +- .../serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md index cd6e63a9b6ae..1510d6485257 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md @@ -231,7 +231,7 @@ You can customize the container by building your own Dockerfile. In your Anyscal ```yaml # service.yaml # Replace: -# image_uri: anyscale/ray-llm:2.49.0-py311-cu128 +# image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # with: containerfile: ./Dockerfile diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb index 0afe561d6542..8a1281123aa6 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb @@ -305,7 +305,7 @@ "```yaml\n", "# service.yaml\n", "# Replace:\n", - "# image_uri: anyscale/ray-llm:2.49.0-py311-cu128\n", + "# image_uri: anyscale/ray-llm:2.52.0-py311-cu128\n", "\n", "# with:\n", "containerfile: ./Dockerfile\n", From 4a61221a2b7440fffb4c12ca0c33e893ec02c279 Mon Sep 17 00:00:00 2001 From: Aydin Abiar Date: Tue, 2 Dec 2025 22:35:33 -0800 Subject: [PATCH 3/5] change image tag in commented code Signed-off-by: Aydin Abiar --- .../serve/tutorials/deployment-serve-llm/gpt-oss/README.md | 4 ++-- .../tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md index 1510d6485257..fbe0aba60e1b 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md @@ -206,7 +206,7 @@ Create your Anyscale Service configuration in a new `service.yaml` file: ```yaml # service.yaml -name: deploy-llama-3-8b +name: deploy-gpt-oss 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 @@ -214,7 +214,7 @@ working_dir: . cloud: applications: # Point to your app in your Python module - - import_path: serve_llama_3_1_8b:app + - import_path: serve_gpt_oss:app ``` diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb index 8a1281123aa6..b7646bc4c295 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb @@ -269,7 +269,7 @@ "\n", "```yaml\n", "# service.yaml\n", - "name: deploy-llama-3-8b\n", + "name: deploy-gpt-oss\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", @@ -277,7 +277,7 @@ "cloud:\n", "applications:\n", " # Point to your app in your Python module\n", - " - import_path: serve_llama_3_1_8b:app\n", + " - import_path: serve_gpt_oss:app\n", "```\n", "\n", "\n", From 0edf18e86f0aeb8adf51ffb1066b227456d1c408 Mon Sep 17 00:00:00 2001 From: Aydin Abiar <62435714+Aydin-ab@users.noreply.github.com> Date: Wed, 3 Dec 2025 13:39:11 -0800 Subject: [PATCH 4/5] Update doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb Co-authored-by: kunling-anyscale Signed-off-by: Aydin Abiar <62435714+Aydin-ab@users.noreply.github.com> --- .../serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb index b7646bc4c295..50d9b5c9862d 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb @@ -300,7 +300,7 @@ "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", + "You can customize the container by building your own Dockerfile. In your Anyscale Service config file `service.yaml`, reference the Dockerfile with `containerfile` (instead of `image_uri`):\n", "\n", "```yaml\n", "# service.yaml\n", From a9db2dfb8d9c6d80c1a89eb3a47cfc52a90da6f3 Mon Sep 17 00:00:00 2001 From: Aydin Abiar Date: Wed, 3 Dec 2025 13:42:07 -0800 Subject: [PATCH 5/5] change grammar Signed-off-by: Aydin Abiar --- .../serve/tutorials/deployment-serve-llm/gpt-oss/README.md | 4 ++-- .../tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb | 2 +- .../serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml | 2 +- .../tutorials/deployment-serve-llm/large-size-llm/README.md | 2 +- .../deployment-serve-llm/large-size-llm/notebook.ipynb | 2 +- .../deployment-serve-llm/large-size-llm/service.yaml | 2 +- .../tutorials/deployment-serve-llm/medium-size-llm/README.md | 2 +- .../deployment-serve-llm/medium-size-llm/notebook.ipynb | 2 +- .../deployment-serve-llm/medium-size-llm/service.yaml | 2 +- .../tutorials/deployment-serve-llm/small-size-llm/README.md | 2 +- .../deployment-serve-llm/small-size-llm/notebook.ipynb | 2 +- .../deployment-serve-llm/small-size-llm/service.yaml | 2 +- 12 files changed, 13 insertions(+), 13 deletions(-) diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md index fbe0aba60e1b..7174361ebbf0 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/README.md @@ -207,7 +207,7 @@ Create your Anyscale Service configuration in a new `service.yaml` file: ```yaml # service.yaml name: deploy-gpt-oss -image_uri: anyscale/ray-llm:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true working_dir: . @@ -226,7 +226,7 @@ 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`): +You can customize the container by building your own Dockerfile. In your Anyscale Service config file `service.yaml`, reference the Dockerfile with `containerfile` (instead of `image_uri`): ```yaml # service.yaml diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb index 50d9b5c9862d..28b08e0c7a2c 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/notebook.ipynb @@ -270,7 +270,7 @@ "```yaml\n", "# service.yaml\n", "name: deploy-gpt-oss\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", + "image_uri: anyscale/ray-llm:2.52.0-py311-cu128 # Anyscale Ray Serve LLM image. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile`\n", "compute_config:\n", " auto_select_worker_config: true \n", "working_dir: .\n", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml index e22a2087efc4..2ac69a1f2608 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml +++ b/doc/source/serve/tutorials/deployment-serve-llm/gpt-oss/service.yaml @@ -1,6 +1,6 @@ # service.yaml name: deploy-gpt-oss -image_uri: anyscale/ray-llm:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true working_dir: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/README.md b/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/README.md index 6f327451cb44..51f3ac01c9d9 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/README.md +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true # Change default disk size to 1000GB diff --git a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/notebook.ipynb index a07e660c3462..5f7b9b796eba 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/notebook.ipynb +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile`\n", "compute_config:\n", " auto_select_worker_config: true \n", " # Change default disk size to 1000GB\n", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/service.yaml index 5c43377cc564..6462f45713e2 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/large-size-llm/service.yaml +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true # Change default disk size to 1000GB diff --git a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/README.md b/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/README.md index d49bb1167cfd..0a71ab46a31b 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/README.md +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true working_dir: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/notebook.ipynb index 037e57448f72..6785124683d6 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/notebook.ipynb +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile`\n", "compute_config:\n", " auto_select_worker_config: true \n", "working_dir: .\n", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/service.yaml index f8a08a95418c..80a19f5f72e6 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/medium-size-llm/service.yaml +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true working_dir: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/README.md b/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/README.md index fa9d39c91535..a1a77f367f46 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/README.md +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true working_dir: . diff --git a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/notebook.ipynb b/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/notebook.ipynb index 010c16d3f139..d7744da49690 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/notebook.ipynb +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile`\n", "compute_config:\n", " auto_select_worker_config: true \n", "working_dir: .\n", diff --git a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/service.yaml b/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/service.yaml index a3e0f3dbc123..b1fc3fa2d6c8 100644 --- a/doc/source/serve/tutorials/deployment-serve-llm/small-size-llm/service.yaml +++ b/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:2.52.0-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. To build an image from a custom Dockerfile, set `containerfile: ./Dockerfile` compute_config: auto_select_worker_config: true working_dir: .