Add support for RamaLama

RamaLama is a fully Open Source AI Model tool that facilitate
local management of AI Models.

https://github.com/containers/ramalama

It is fully open source and supports pulling models from HuggingFace,
Ollama, OCI Images, and via URI file://, http://, https://

It uses the llama.cpp and vllm AI engines for running the MODELS.

It also defaults to running the models inside of containers.

Signed-off-by: Daniel J Walsh <dwalsh@redhat.com>

llama_stack/templates/ramalama/build.yaml

@@ -0,0 +1,31 @@
+version: '2'
+distribution_spec:
+  description: Use (an external) RamaLama server for running LLM inference
+  providers:
+    inference:
+    - remote::ramalama
+    vector_io:
+    - inline::faiss
+    - remote::chromadb
+    - remote::pgvector
+    safety:
+    - inline::llama-guard
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+    eval:
+    - inline::meta-reference
+    datasetio:
+    - remote::huggingface
+    - inline::localfs
+    scoring:
+    - inline::basic
+    - inline::llm-as-judge
+    - inline::braintrust
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - inline::code-interpreter
+    - inline::rag-runtime
+image_type: conda