Merge branch 'main' into clarifai-inference-provider

llama_stack/distribution/templates/docker/llamastack-local-cpu/build.yaml

@@ -1,15 +0,0 @@
-name: local-cpu
-distribution_spec:
-  description: remote inference + local safety/agents/memory
-  docker_image: null
-  providers:
-    inference:
-    - remote::ollama
-    - remote::tgi
-    - remote::together
-    - remote::fireworks
-    safety: meta-reference
-    agents: meta-reference
-    memory: meta-reference
-    telemetry: meta-reference
-image_type: docker

llama_stack/distribution/templates/docker/llamastack-local-cpu/run.yaml

@@ -1,49 +0,0 @@
-built_at: '2024-09-30T09:04:30.533391'
-image_name: local-cpu
-docker_image: local-cpu
-conda_env: null
-apis_to_serve:
-- agents
-- inference
-- models
-- memory
-- safety
-- shields
-- memory_banks
-api_providers:
-  inference:
-    providers:
-    - remote::ollama
-  safety:
-    providers:
-    - meta-reference
-  agents:
-    provider_type: meta-reference
-    config:
-      persistence_store:
-        namespace: null
-        type: sqlite
-        db_path: ~/.llama/runtime/kvstore.db
-  memory:
-    providers:
-    - meta-reference
-  telemetry:
-    provider_type: meta-reference
-    config: {}
-routing_table:
-  inference:
-  - provider_type: remote::ollama
-    config:
-      host: localhost
-      port: 6000
-    routing_key: Llama3.1-8B-Instruct
-  safety:
-  - provider_type: meta-reference
-    config:
-      llama_guard_shield: null
-      prompt_guard_shield: null
-    routing_key: ["llama_guard", "code_scanner_guard", "injection_shield", "jailbreak_shield"]
-  memory:
-  - provider_type: meta-reference
-    config: {}
-    routing_key: vector

llama_stack/distribution/templates/docker/llamastack-local-gpu/build.yaml

@@ -1,11 +0,0 @@
-name: local-gpu
-distribution_spec:
-  description: local meta reference
-  docker_image: null
-  providers:
-    inference: meta-reference
-    safety: meta-reference
-    agents: meta-reference
-    memory: meta-reference
-    telemetry: meta-reference
-image_type: docker

llama_stack/distribution/templates/docker/llamastack-local-gpu/run.yaml

@@ -1,52 +0,0 @@
-built_at: '2024-09-30T09:00:56.693751'
-image_name: local-gpu
-docker_image: local-gpu
-conda_env: null
-apis_to_serve:
-- memory
-- inference
-- agents
-- shields
-- safety
-- models
-- memory_banks
-api_providers:
-  inference:
-    providers:
-    - meta-reference
-  safety:
-    providers:
-    - meta-reference
-  agents:
-    provider_type: meta-reference
-    config:
-      persistence_store:
-        namespace: null
-        type: sqlite
-        db_path: ~/.llama/runtime/kvstore.db
-  memory:
-    providers:
-    - meta-reference
-  telemetry:
-    provider_type: meta-reference
-    config: {}
-routing_table:
-  inference:
-  - provider_type: meta-reference
-    config:
-      model: Llama3.1-8B-Instruct
-      quantization: null
-      torch_seed: null
-      max_seq_len: 4096
-      max_batch_size: 1
-    routing_key: Llama3.1-8B-Instruct
-  safety:
-  - provider_type: meta-reference
-    config:
-      llama_guard_shield: null
-      prompt_guard_shield: null
-    routing_key: ["llama_guard", "code_scanner_guard", "injection_shield", "jailbreak_shield"]
-  memory:
-  - provider_type: meta-reference
-    config: {}
-    routing_key: vector

llama_stack/distribution/templates/local-bedrock-conda-example-build.yaml

@@ -1,10 +0,0 @@
-name: local-bedrock-conda-example
-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/distribution/templates/local-build.yaml

@@ -1,10 +0,0 @@
-name: local
-distribution_spec:
-  description: Use code from `llama_stack` itself to serve all llama stack APIs
-  providers:
-    inference: meta-reference
-    memory: meta-reference
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference
-image_type: conda

llama_stack/distribution/templates/local-databricks-build.yaml

@@ -1,10 +0,0 @@
-name: local-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/distribution/templates/local-fireworks-build.yaml

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

llama_stack/distribution/templates/local-hf-endpoint-build.yaml

@@ -1,10 +0,0 @@
-name: local-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/distribution/templates/local-hf-serverless-build.yaml

@@ -1,10 +0,0 @@
-name: local-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/distribution/templates/local-ollama-build.yaml

@@ -1,10 +0,0 @@
-name: local-ollama
-distribution_spec:
-  description: Like local, but use ollama for running LLM inference
-  providers:
-    inference: remote::ollama
-    memory: meta-reference
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference
-image_type: conda

llama_stack/distribution/templates/local-tgi-build.yaml

@@ -1,10 +0,0 @@
-name: local-tgi
-distribution_spec:
-  description: Like local, but use a TGI server for running LLM inference.
-  providers:
-    inference: remote::tgi
-    memory: meta-reference
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference
-image_type: conda

llama_stack/distribution/templates/local-together-build.yaml

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

llama_stack/distribution/templates/local-vllm-build.yaml

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