feat: consolidate most distros into "starter" (#2516)

# What does this PR do?

* Removes a bunch of distros
* Removed distros were added into the "starter" distribution
* Doc for "starter" has been added
* Partially reverts https://github.com/meta-llama/llama-stack/pull/2482
  since inference providers are disabled by default and can be turned on
  manually via env variable.
* Disables safety in starter distro

Closes: https://github.com/meta-llama/llama-stack/issues/2502.

~Needs: https://github.com/meta-llama/llama-stack/pull/2482 for Ollama
to work properly in the CI.~

TODO:

- [ ] We can only update `install.sh` when we get a new release.
- [x] Update providers documentation
- [ ] Update notebooks to reference starter instead of ollama

Signed-off-by: Sébastien Han <seb@redhat.com>

llama_stack/templates/starter/build.yaml

@@ -3,15 +3,30 @@ distribution_spec:
   description: Quick start template for running Llama Stack with several popular providers
   providers:
     inference:
-    - remote::openai
+    - remote::cerebras
+    - remote::ollama
+    - remote::vllm
+    - remote::tgi
+    - remote::hf::serverless
+    - remote::hf::endpoint
     - remote::fireworks
     - remote::together
-    - remote::ollama
+    - remote::bedrock
+    - remote::databricks
+    - remote::nvidia
+    - remote::runpod
+    - remote::openai
     - remote::anthropic
     - remote::gemini
     - remote::groq
+    - remote::fireworks-openai-compat
+    - remote::llama-openai-compat
+    - remote::together-openai-compat
+    - remote::groq-openai-compat
+    - remote::sambanova-openai-compat
+    - remote::cerebras-openai-compat
     - remote::sambanova
-    - remote::vllm
+    - remote::passthrough
     - inline::sentence-transformers
     vector_io:
     - inline::sqlite-vec
@@ -26,6 +41,8 @@ distribution_spec:
     - inline::meta-reference
     telemetry:
     - inline::meta-reference
+    post_training:
+    - inline::huggingface
     eval:
     - inline::meta-reference
     datasetio: