Update doc templates for running safety on self-hosted templates (#874)

docs/source/distributions/self_hosted_distro/ollama.md

@@ -1,3 +1,6 @@
+---
+orphan: true
+---
 # Ollama Distribution
 
 ```{toctree}
@@ -79,11 +82,15 @@ docker run \
 If you are using Llama Stack Safety / Shield APIs, use:
 
 ```bash
+# You need a local checkout of llama-stack to run this, get it using
+# git clone https://github.com/meta-llama/llama-stack.git
+cd /path/to/llama-stack
+
 docker run \
   -it \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
-  -v ./run-with-safety.yaml:/root/my-run.yaml \
+  -v ./llama_stack/templates/ollama/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-ollama \
   --yaml-config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \

docs/source/distributions/self_hosted_distro/remote-vllm.md

@@ -1,3 +1,6 @@
+---
+orphan: true
+---
 # Remote vLLM Distribution
 ```{toctree}
 :maxdepth: 2
@@ -107,10 +110,15 @@ If you are using Llama Stack Safety / Shield APIs, use:
 export SAFETY_PORT=8081
 export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 
+# You need a local checkout of llama-stack to run this, get it using
+# git clone https://github.com/meta-llama/llama-stack.git
+cd /path/to/llama-stack
+
 docker run \
   -it \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-  -v ./run-with-safety.yaml:/root/my-run.yaml \
+  -v ~/.llama:/root/.llama \
+  -v ./llama_stack/templates/remote-vllm/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-remote-vllm \
   --yaml-config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \

docs/source/distributions/self_hosted_distro/sambanova.md

@@ -16,9 +16,10 @@ The `llamastack/distribution-sambanova` distribution consists of the following p
 |-----|-------------|
 | agents | `inline::meta-reference` |
 | inference | `remote::sambanova` |
-| memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 | safety | `inline::llama-guard` |
 | telemetry | `inline::meta-reference` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
+| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 
 ### Environment Variables
@@ -32,13 +33,13 @@ The following environment variables can be configured:
 
 The following models are available by default:
 
-- `meta-llama/Llama-3.1-8B-Instruct`
-- `meta-llama/Llama-3.1-70B-Instruct`
-- `meta-llama/Llama-3.1-405B-Instruct`
-- `meta-llama/Llama-3.2-1B-Instruct`
-- `meta-llama/Llama-3.2-3B-Instruct`
-- `meta-llama/Llama-3.2-11B-Vision-Instruct`
-- `meta-llama/Llama-3.2-90B-Vision-Instruct`
+- `meta-llama/Llama-3.1-8B-Instruct (Meta-Llama-3.1-8B-Instruct)`
+- `meta-llama/Llama-3.1-70B-Instruct (Meta-Llama-3.1-70B-Instruct)`
+- `meta-llama/Llama-3.1-405B-Instruct-FP8 (Meta-Llama-3.1-405B-Instruct)`
+- `meta-llama/Llama-3.2-1B-Instruct (Meta-Llama-3.2-1B-Instruct)`
+- `meta-llama/Llama-3.2-3B-Instruct (Meta-Llama-3.2-3B-Instruct)`
+- `meta-llama/Llama-3.2-11B-Vision-Instruct (Llama-3.2-11B-Vision-Instruct)`
+- `meta-llama/Llama-3.2-90B-Vision-Instruct (Llama-3.2-90B-Vision-Instruct)`
 
 
 ### Prerequisite: API Keys

docs/source/distributions/self_hosted_distro/tgi.md

@@ -1,3 +1,7 @@
+---
+orphan: true
+---
+
 # TGI Distribution
 
 ```{toctree}
@@ -98,10 +102,15 @@ docker run \
 If you are using Llama Stack Safety / Shield APIs, use:
 
 ```bash
+# You need a local checkout of llama-stack to run this, get it using
+# git clone https://github.com/meta-llama/llama-stack.git
+cd /path/to/llama-stack
+
 docker run \
   -it \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-  -v ./run-with-safety.yaml:/root/my-run.yaml \
+  -v ~/.llama:/root/.llama \
+  -v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
   llamastack/distribution-tgi \
   --yaml-config /root/my-run.yaml \
   --port $LLAMA_STACK_PORT \

docs/source/distributions/self_hosted_distro/together.md

@@ -1,3 +1,6 @@
+---
+orphan: true
+---
 # Together Distribution
 
 ```{toctree}