fix broken --list-templates with adding build.yaml files for packaging (#327)

* add build files to templates

* fix templates

* manifest

* symlink

* symlink

* precommit

* change everything to docker build.yaml

* remove image_type in templates

* fix build from templates CLI

* fix readmes

distributions/bedrock/build.yaml

@@ -1,10 +0,0 @@
-name: bedrock
-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

distributions/bedrock/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/bedrock/build.yaml

distributions/databricks/build.yaml

@@ -1,10 +0,0 @@
-name: 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

distributions/databricks/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/databricks/build.yaml

distributions/fireworks/README.md

@@ -49,7 +49,7 @@ inference:
 **Via Conda**
 
 ```bash
-llama stack build --config ./build.yaml
+llama stack build --template fireworks --image-type conda
 # -- modify run.yaml to a valid Fireworks server endpoint
 llama stack run ./run.yaml
 ```

distributions/fireworks/build.yaml

@@ -1,10 +0,0 @@
-name: 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: docker

distributions/fireworks/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/fireworks/build.yaml

distributions/hf-endpoint/build.yaml

@@ -1,10 +0,0 @@
-name: 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

distributions/hf-endpoint/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/hf-endpoint/build.yaml

distributions/hf-serverless/build.yaml

@@ -1,10 +0,0 @@
-name: 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

distributions/hf-serverless/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/hf-serverless/build.yaml

distributions/meta-reference-gpu/build.yaml

@@ -1,14 +0,0 @@
-name: meta-reference-gpu
-distribution_spec:
-  docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
-  description: Use code from `llama_stack` itself to serve all llama stack APIs
-  providers:
-    inference: meta-reference
-    memory:
-    - meta-reference
-    - remote::chromadb
-    - remote::pgvector
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference
-image_type: docker

distributions/meta-reference-gpu/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/meta-reference-gpu/build.yaml

distributions/meta-reference-quantized-gpu/build.yaml

@@ -1,14 +0,0 @@
-name: meta-reference-quantized-gpu
-distribution_spec:
-  docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
-  description: Use code from `llama_stack` itself to serve all llama stack APIs
-  providers:
-    inference: meta-reference-quantized
-    memory:
-    - meta-reference
-    - remote::chromadb
-    - remote::pgvector
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference
-image_type: docker

distributions/meta-reference-quantized-gpu/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/meta-reference-quantized-gpu/build.yaml

distributions/ollama/README.md

@@ -86,6 +86,6 @@ inference:
 **Via Conda**
 
 ```
-llama stack build --config ./build.yaml
+llama stack build --template ollama --image-type conda
 llama stack run ./gpu/run.yaml
 ```

distributions/ollama/build.yaml

@@ -1,13 +0,0 @@
-name: ollama
-distribution_spec:
-  description: Use ollama for running LLM inference
-  providers:
-    inference: remote::ollama
-    memory:
-    - meta-reference
-    - remote::chromadb
-    - remote::pgvector
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference
-image_type: docker

distributions/ollama/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/ollama/build.yaml

distributions/tgi/README.md

@@ -88,7 +88,7 @@ inference:
 **Via Conda**
 
 ```bash
-llama stack build --config ./build.yaml
+llama stack build --template tgi --image-type conda
 # -- start a TGI server endpoint
 llama stack run ./gpu/run.yaml
 ```

distributions/tgi/build.yaml

@@ -1,13 +0,0 @@
-name: tgi
-distribution_spec:
-  description: Use TGI for running LLM inference
-  providers:
-    inference: remote::tgi
-    memory:
-    - meta-reference
-    - remote::chromadb
-    - remote::pgvector
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference
-image_type: docker

distributions/tgi/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/tgi/build.yaml

distributions/together/README.md

@@ -62,7 +62,7 @@ memory:
 **Via Conda**
 
 ```bash
-llama stack build --config ./build.yaml
+llama stack build --template together --image-type conda
 # -- modify run.yaml to a valid Together server endpoint
 llama stack run ./run.yaml
 ```

distributions/together/build.yaml

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

distributions/together/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/together/build.yaml

distributions/vllm/build.yaml

@@ -1,10 +0,0 @@
-name: 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

distributions/vllm/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/vllm/build.yaml