forked from phoenix-oss/llama-stack-mirror
eb2d8a31a5
* Update configure.py to use multiple routing keys for safety * Refactor distribution/datatypes into a providers/datatypes * Cleanup
52 lines
1.1 KiB
YAML
52 lines
1.1 KiB
YAML
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_id: meta-reference
|
|
config:
|
|
persistence_store:
|
|
namespace: null
|
|
type: sqlite
|
|
db_path: /home/xiyan/.llama/runtime/kvstore.db
|
|
memory:
|
|
providers:
|
|
- meta-reference
|
|
telemetry:
|
|
provider_id: meta-reference
|
|
config: {}
|
|
routing_table:
|
|
inference:
|
|
- provider_id: 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_id: meta-reference
|
|
config:
|
|
llama_guard_shield: null
|
|
prompt_guard_shield: null
|
|
routing_key: ["llama_guard", "code_scanner_guard", "injection_shield", "jailbreak_shield"]
|
|
memory:
|
|
- provider_id: meta-reference
|
|
config: {}
|
|
routing_key: vector
|