diff --git a/distributions/bedrock/build.yaml b/distributions/bedrock/build.yaml deleted file mode 100644 index ae7b27d49..000000000 --- a/distributions/bedrock/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/bedrock/build.yaml b/distributions/bedrock/build.yaml new file mode 120000 index 000000000..72402ef8d --- /dev/null +++ b/distributions/bedrock/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/bedrock/build.yaml \ No newline at end of file diff --git a/distributions/databricks/build.yaml b/distributions/databricks/build.yaml deleted file mode 100644 index 2188dd0a0..000000000 --- a/distributions/databricks/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/databricks/build.yaml b/distributions/databricks/build.yaml new file mode 120000 index 000000000..66342fe6f --- /dev/null +++ b/distributions/databricks/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/databricks/build.yaml \ No newline at end of file diff --git a/distributions/fireworks/build.yaml b/distributions/fireworks/build.yaml deleted file mode 100644 index 2e5cf0753..000000000 --- a/distributions/fireworks/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/fireworks/build.yaml b/distributions/fireworks/build.yaml new file mode 120000 index 000000000..32a5bd869 --- /dev/null +++ b/distributions/fireworks/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/fireworks/build.yaml \ No newline at end of file diff --git a/distributions/hf-endpoint/build.yaml b/distributions/hf-endpoint/build.yaml deleted file mode 100644 index 750bebcb5..000000000 --- a/distributions/hf-endpoint/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/hf-endpoint/build.yaml b/distributions/hf-endpoint/build.yaml new file mode 120000 index 000000000..a73c70c05 --- /dev/null +++ b/distributions/hf-endpoint/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/hf-endpoint/build.yaml \ No newline at end of file diff --git a/distributions/hf-serverless/build.yaml b/distributions/hf-serverless/build.yaml deleted file mode 100644 index f6da3ad4d..000000000 --- a/distributions/hf-serverless/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/hf-serverless/build.yaml b/distributions/hf-serverless/build.yaml new file mode 120000 index 000000000..f2db0fd55 --- /dev/null +++ b/distributions/hf-serverless/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/hf-serverless/build.yaml \ No newline at end of file diff --git a/distributions/meta-reference-gpu/build.yaml b/distributions/meta-reference-gpu/build.yaml deleted file mode 100644 index 08e034154..000000000 --- a/distributions/meta-reference-gpu/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/meta-reference-quantized-gpu/build.yaml b/distributions/meta-reference-quantized-gpu/build.yaml deleted file mode 100644 index e9ddb4aad..000000000 --- a/distributions/meta-reference-quantized-gpu/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/ollama/build.yaml b/distributions/ollama/build.yaml deleted file mode 100644 index c27f40929..000000000 --- a/distributions/ollama/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/ollama/build.yaml b/distributions/ollama/build.yaml new file mode 120000 index 000000000..8772548e0 --- /dev/null +++ b/distributions/ollama/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/ollama/build.yaml \ No newline at end of file diff --git a/distributions/tgi/build.yaml b/distributions/tgi/build.yaml deleted file mode 100644 index 2c0ca1d33..000000000 --- a/distributions/tgi/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/tgi/build.yaml b/distributions/tgi/build.yaml new file mode 120000 index 000000000..73e59ad84 --- /dev/null +++ b/distributions/tgi/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/tgi/build.yaml \ No newline at end of file diff --git a/distributions/together/build.yaml b/distributions/together/build.yaml deleted file mode 100644 index 49eab859d..000000000 --- a/distributions/together/build.yaml +++ /dev/null @@ -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 diff --git a/distributions/together/build.yaml b/distributions/together/build.yaml new file mode 120000 index 000000000..3877a9c96 --- /dev/null +++ b/distributions/together/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/together/build.yaml \ No newline at end of file diff --git a/distributions/vllm/build.yaml b/distributions/vllm/build.yaml deleted file mode 100644 index f41352eb1..000000000 --- a/distributions/vllm/build.yaml +++ /dev/null @@ -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 \ No newline at end of file diff --git a/distributions/vllm/build.yaml b/distributions/vllm/build.yaml new file mode 120000 index 000000000..dfc9401b6 --- /dev/null +++ b/distributions/vllm/build.yaml @@ -0,0 +1 @@ +../../llama_stack/templates/vllm/build.yaml \ No newline at end of file