config templates restructure, docs (#262)

* wip

* config templates

* readmes

llama_stack/distribution/templates/build_configs/local-bedrock-conda-example-build.yaml

@@ -0,0 +1,10 @@
+name: local-bedrock-conda-example
+distribution_spec:
+  description: Use Amazon Bedrock APIs.
+  providers:
+    inference: remote::bedrock
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-cpu-docker-build.yaml

@@ -0,0 +1,15 @@
+name: local-cpu
+distribution_spec:
+  description: remote inference + local safety/agents/memory
+  docker_image: null
+  providers:
+    inference:
+    - remote::ollama
+    - remote::tgi
+    - remote::together
+    - remote::fireworks
+    safety: meta-reference
+    agents: meta-reference
+    memory: meta-reference
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/build_configs/local-databricks-build.yaml

@@ -0,0 +1,10 @@
+name: local-databricks
+distribution_spec:
+  description: Use Databricks for running LLM inference
+  providers:
+    inference: remote::databricks
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-fireworks-build.yaml

@@ -0,0 +1,10 @@
+name: local-fireworks
+distribution_spec:
+  description: Use Fireworks.ai for running LLM inference
+  providers:
+    inference: remote::fireworks
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-gpu-docker-build.yaml

@@ -0,0 +1,10 @@
+name: local-gpu
+distribution_spec:
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
+  providers:
+    inference: meta-reference
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/build_configs/local-hf-endpoint-build.yaml

@@ -0,0 +1,10 @@
+name: local-hf-endpoint
+distribution_spec:
+  description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
+  providers:
+    inference: remote::hf::endpoint
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-hf-serverless-build.yaml

@@ -0,0 +1,10 @@
+name: local-hf-serverless
+distribution_spec:
+  description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
+  providers:
+    inference: remote::hf::serverless
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-ollama-build.yaml

@@ -0,0 +1,10 @@
+name: local-ollama
+distribution_spec:
+  description: Like local, but use ollama for running LLM inference
+  providers:
+    inference: remote::ollama
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-tgi-build.yaml

@@ -0,0 +1,10 @@
+name: local-tgi
+distribution_spec:
+  description: Like local, but use a TGI server for running LLM inference.
+  providers:
+    inference: remote::tgi
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-tgi-chroma-docker-build.yaml

@@ -0,0 +1,11 @@
+name: local-tgi-chroma
+distribution_spec:
+  description: remote tgi inference + chromadb memory
+  docker_image: null
+  providers:
+    inference: remote::tgi
+    safety: meta-reference
+    agents: meta-reference
+    memory: remote::chromadb
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/build_configs/local-together-build.yaml

@@ -0,0 +1,10 @@
+name: local-together
+distribution_spec:
+  description: Use Together.ai for running LLM inference
+  providers:
+    inference: remote::together
+    memory: meta-reference
+    safety: remote::together
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/distribution/templates/build_configs/local-vllm-build.yaml

@@ -0,0 +1,10 @@
+name: local-vllm
+distribution_spec:
+  description: Like local, but use vLLM for running LLM inference
+  providers:
+    inference: vllm
+    memory: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda