move build.yaml to templates, symlink in distributions

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/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
-  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/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/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/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

llama_stack/cli/stack/build.py

@@ -12,15 +12,7 @@ import os
 from functools import lru_cache
 from pathlib import Path
 
-TEMPLATES_PATH = (
-    Path(os.path.relpath(__file__)).parent.parent.parent.parent / "distributions----"
-)
-
-# build.yaml templates exist in the llama-stack/distributions while wheel installs llama-stack/llama_stack
-# we copied the distributions folder to llama-stack/llama_stack/cli/distributions for wheel builds,
-# so we need to check both locations
-if not TEMPLATES_PATH.exists():
-    TEMPLATES_PATH = Path(os.path.relpath(__file__)).parent.parent.parent / "templates"
+TEMPLATES_PATH = Path(os.path.relpath(__file__)).parent.parent.parent / "templates"
 
 
 @lru_cache()

llama_stack/templates/bedrock/build.yaml

@@ -1 +0,0 @@
-../../distributions/bedrock/build.yaml

llama_stack/templates/bedrock/build.yaml

@@ -0,0 +1,10 @@
+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

llama_stack/templates/databricks/build.yaml

@@ -0,0 +1,10 @@
+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

llama_stack/templates/fireworks/build.yaml

@@ -1 +0,0 @@
-../../distributions/fireworks/build.yaml

llama_stack/templates/fireworks/build.yaml

@@ -0,0 +1,10 @@
+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

llama_stack/templates/hf-endpoint/build.yaml

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

llama_stack/templates/hf-endpoint/build.yaml

@@ -0,0 +1,10 @@
+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

llama_stack/templates/hf-serverless/build.yaml

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

llama_stack/templates/hf-serverless/build.yaml

@@ -0,0 +1,10 @@
+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

llama_stack/templates/meta-reference-gpu/build.yaml

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

llama_stack/templates/meta-reference-gpu/build.yaml

@@ -0,0 +1,14 @@
+name: meta-reference-gpu
+distribution_spec:
+  docker_image: pytorch/pytorch
+  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

llama_stack/templates/meta-reference-quantized-gpu/build.yaml

@@ -0,0 +1,14 @@
+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

llama_stack/templates/ollama/build.yaml

@@ -1 +0,0 @@
-../../distributions/ollama/build.yaml

llama_stack/templates/ollama/build.yaml

@@ -0,0 +1,13 @@
+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

llama_stack/templates/tgi/build.yaml

@@ -1 +0,0 @@
-../../distributions/tgi/build.yaml

llama_stack/templates/tgi/build.yaml

@@ -0,0 +1,13 @@
+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

llama_stack/templates/together/build.yaml

@@ -1 +0,0 @@
-../../distributions/together/build.yaml

llama_stack/templates/together/build.yaml

@@ -0,0 +1,10 @@
+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

llama_stack/templates/vllm/build.yaml

@@ -1 +0,0 @@
-../../distributions/vllm/build.yaml

llama_stack/templates/vllm/build.yaml

@@ -0,0 +1,10 @@
+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