More generic image type for OCI-compliant container technologies (#802)

It's a more generic term and applicable to alternatives of Docker, such as Podman or other OCI-compliant technologies. --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
2025-01-17 19:37:42 -05:00 · 2025-01-17 19:37:42 -05:00 · 6da3053c0e
commit 6da3053c0e
parent 9d005154d7
30 changed files with 102 additions and 100 deletions
--- a/llama_stack/templates/bedrock/bedrock.py
+++ b/llama_stack/templates/bedrock/bedrock.py
@ -70,7 +70,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use AWS Bedrock for running LLM inference and safety",
-        docker_image=None,
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        default_models=default_models,
--- a/llama_stack/templates/cerebras/cerebras.py
+++ b/llama_stack/templates/cerebras/cerebras.py
@ -92,7 +92,7 @@ def get_distribution_template() -> DistributionTemplate:
        name="cerebras",
        distro_type="self_hosted",
        description="Use Cerebras for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        default_models=default_models,
--- a/llama_stack/templates/experimental-post-training/build.yaml
+++ b/llama_stack/templates/experimental-post-training/build.yaml
@ -2,7 +2,7 @@ version: '2'
 name: experimental-post-training
 distribution_spec:
  description: Experimental template for post training
-  docker_image: null
+  container_image: null
  providers:
    inference:
    - inline::meta-reference
--- a/llama_stack/templates/experimental-post-training/run.yaml
+++ b/llama_stack/templates/experimental-post-training/run.yaml
@ -1,6 +1,6 @@
 version: '2'
 image_name: experimental-post-training
-docker_image: null
+container_image: null
 conda_env: experimental-post-training
 apis:
 - agents
--- a/llama_stack/templates/fireworks/fireworks.py
+++ b/llama_stack/templates/fireworks/fireworks.py
@ -98,7 +98,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use Fireworks.AI for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        default_models=default_models,
--- a/llama_stack/templates/hf-endpoint/hf_endpoint.py
+++ b/llama_stack/templates/hf-endpoint/hf_endpoint.py
@ -88,7 +88,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use (an external) Hugging Face Inference Endpoint for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=None,
        providers=providers,
        default_models=[inference_model, safety_model],
--- a/llama_stack/templates/hf-serverless/hf_serverless.py
+++ b/llama_stack/templates/hf-serverless/hf_serverless.py
@ -89,7 +89,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use (an external) Hugging Face Inference Endpoint for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=None,
        providers=providers,
        default_models=[inference_model, safety_model],
--- a/llama_stack/templates/nvidia/nvidia.py
+++ b/llama_stack/templates/nvidia/nvidia.py
@ -68,7 +68,7 @@ def get_distribution_template() -> DistributionTemplate:
        name="nvidia",
        distro_type="remote_hosted",
        description="Use NVIDIA NIM for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        default_models=default_models,
--- a/llama_stack/templates/ollama/ollama.py
+++ b/llama_stack/templates/ollama/ollama.py
@ -90,7 +90,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use (an external) Ollama server for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        default_models=[inference_model, safety_model],
--- a/llama_stack/templates/template.py
+++ b/llama_stack/templates/template.py
@ -37,7 +37,7 @@ class RunConfigSettings(BaseModel):
        self,
        name: str,
        providers: Dict[str, List[str]],
-        docker_image: Optional[str] = None,
+        container_image: Optional[str] = None,
    ) -> StackRunConfig:
        provider_registry = get_provider_registry()

@ -83,7 +83,7 @@ class RunConfigSettings(BaseModel):

        return StackRunConfig(
            image_name=name,
-            docker_image=docker_image,
+            container_image=container_image,
            conda_env=name,
            apis=apis,
            providers=provider_configs,
@ -113,7 +113,7 @@ class DistributionTemplate(BaseModel):

    # Optional configuration
    run_config_env_vars: Optional[Dict[str, Tuple[str, str]]] = None
-    docker_image: Optional[str] = None
+    container_image: Optional[str] = None

    default_models: Optional[List[ModelInput]] = None

@ -122,7 +122,7 @@ class DistributionTemplate(BaseModel):
            name=self.name,
            distribution_spec=DistributionSpec(
                description=self.description,
-                docker_image=self.docker_image,
+                container_image=self.container_image,
                providers=self.providers,
            ),
            image_type="conda",  # default to conda, can be overridden
@ -170,7 +170,7 @@ class DistributionTemplate(BaseModel):

        for yaml_pth, settings in self.run_configs.items():
            run_config = settings.run_config(
-                self.name, self.providers, self.docker_image
+                self.name, self.providers, self.container_image
            )
            with open(yaml_output_dir / yaml_pth, "w") as f:
                yaml.safe_dump(
--- a/llama_stack/templates/tgi/tgi.py
+++ b/llama_stack/templates/tgi/tgi.py
@ -92,7 +92,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use (an external) TGI server for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        default_models=[inference_model, safety_model],
--- a/llama_stack/templates/together/together.py
+++ b/llama_stack/templates/together/together.py
@ -96,7 +96,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use Together.AI for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=Path(__file__).parent / "doc_template.md",
        providers=providers,
        default_models=default_models,
--- a/llama_stack/templates/vllm-gpu/vllm.py
+++ b/llama_stack/templates/vllm-gpu/vllm.py
@ -84,7 +84,7 @@ def get_distribution_template() -> DistributionTemplate:
        name=name,
        distro_type="self_hosted",
        description="Use a built-in vLLM engine for running LLM inference",
-        docker_image=None,
+        container_image=None,
        template_path=None,
        providers=providers,
        default_models=[inference_model],