add more distro templates (#279)

* verify dockers

* together distro verified

* readme

* fireworks distro

* fireworks compose up

* fireworks verified

distributions/ollama/README.md

@@ -71,10 +71,10 @@ ollama run <model_id>
 
 **Via Docker**
 ```
-docker run --network host -it -p 5000:5000 -v ~/.llama:/root/.llama -v ./ollama-run.yaml:/root/llamastack-run-ollama.yaml --gpus=all llamastack-local-cpu --yaml_config /root/llamastack-run-ollama.yaml
+docker run --network host -it -p 5000:5000 -v ~/.llama:/root/.llama -v ./gpu/run.yaml:/root/llamastack-run-ollama.yaml --gpus=all distribution-ollama --yaml_config /root/llamastack-run-ollama.yaml
 ```
 
-Make sure in you `ollama-run.yaml` file, you inference provider is pointing to the correct Ollama endpoint. E.g.
+Make sure in you `run.yaml` file, you inference provider is pointing to the correct Ollama endpoint. E.g.
 ```
 inference:
   - provider_id: ollama0

distributions/ollama/build.yaml

@@ -1,4 +1,4 @@
-name: distribution-ollama
+name: ollama
 distribution_spec:
   description: Use ollama for running LLM inference
   providers:
@@ -10,4 +10,4 @@ distribution_spec:
     safety: meta-reference
     agents: meta-reference
     telemetry: meta-reference
-image_type: conda
+image_type: docker

distributions/ollama/gpu/compose.yaml

@@ -33,7 +33,7 @@ services:
     volumes:
       - ~/.llama:/root/.llama
       # Link to ollama run.yaml file
-      - ./ollama-run.yaml:/root/llamastack-run-ollama.yaml
+      - ./run.yaml:/root/llamastack-run-ollama.yaml
     ports:
       - "5000:5000"
     # Hack: wait for ollama server to start before starting docker