forked from phoenix-oss/llama-stack-mirror
6da3053c0e
It's a more generic term and applicable to alternatives of Docker, such as Podman or other OCI-compliant technologies. --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
66 lines
1.5 KiB
YAML
66 lines
1.5 KiB
YAML
version: '2'
|
|
image_name: local
|
|
container_image: null
|
|
conda_env: local
|
|
apis:
|
|
- shields
|
|
- agents
|
|
- models
|
|
- memory
|
|
- memory_banks
|
|
- inference
|
|
- safety
|
|
providers:
|
|
inference:
|
|
- provider_id: vllm-inference
|
|
provider_type: inline::vllm
|
|
config:
|
|
model: Llama3.2-3B-Instruct
|
|
tensor_parallel_size: 1
|
|
gpu_memory_utilization: 0.4
|
|
enforce_eager: true
|
|
max_tokens: 4096
|
|
- provider_id: vllm-inference-safety
|
|
provider_type: inline::vllm
|
|
config:
|
|
model: Llama-Guard-3-1B
|
|
tensor_parallel_size: 1
|
|
gpu_memory_utilization: 0.2
|
|
enforce_eager: true
|
|
max_tokens: 4096
|
|
safety:
|
|
- provider_id: meta0
|
|
provider_type: inline::llama-guard
|
|
config:
|
|
model: Llama-Guard-3-1B
|
|
excluded_categories: []
|
|
# Uncomment to use prompt guard
|
|
# - provider_id: meta1
|
|
# provider_type: inline::prompt-guard
|
|
# config:
|
|
# model: Prompt-Guard-86M
|
|
memory:
|
|
- provider_id: meta0
|
|
provider_type: inline::meta-reference
|
|
config: {}
|
|
# Uncomment to use pgvector
|
|
# - provider_id: pgvector
|
|
# provider_type: remote::pgvector
|
|
# config:
|
|
# host: 127.0.0.1
|
|
# port: 5432
|
|
# db: postgres
|
|
# user: postgres
|
|
# password: mysecretpassword
|
|
agents:
|
|
- provider_id: meta0
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
namespace: null
|
|
type: sqlite
|
|
db_path: ~/.llama/runtime/agents_store.db
|
|
telemetry:
|
|
- provider_id: meta0
|
|
provider_type: inline::meta-reference
|
|
config: {}
|