phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 04:45:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

skeleton unified routing table, api routers

Browse source
This commit is contained in:
Xi Yan 2024-09-21 13:44:33 -07:00
parent 2dc14cba2c
commit 85d927adde
11 changed files with 210 additions and 231 deletions
Download patch file Download diff file Expand all files Collapse all files

59
llama_stack/examples/router-table-run.yaml
View file

@ -5,7 +5,7 @@ conda_env: local
apis_to_serve:
- inference
# - memory
# - telemetry
- telemetry
provider_map:
telemetry:
provider_id: meta-reference
@ -36,60 +36,3 @@ provider_routing_table:
- routing_key: vector
provider_id: meta-reference
config: {}
# safety:
# provider_id: meta-reference
# config:
# llama_guard_shield:
# model: Llama-Guard-3-8B
# excluded_categories: []
# disable_input_check: false
# disable_output_check: false
# prompt_guard_shield:
# model: Prompt-Guard-86M
# telemetry:
# provider_id: meta-reference
# config: {}
# agents:
# provider_id: meta-reference
# config: {}
# memory:
# provider_id: meta-reference
# config: {}
# models:
# provider_id: builtin
# config:
# models_config:
# - core_model_id: Meta-Llama3.1-8B-Instruct
# provider_id: meta-reference
# api: inference
# config:
# model: Meta-Llama3.1-8B-Instruct
# quantization: null
# torch_seed: null
# max_seq_len: 4096
# max_batch_size: 1
# - core_model_id: Meta-Llama3.1-8B
# provider_id: meta-reference
# api: inference
# config:
# model: Meta-Llama3.1-8B
# quantization: null
# torch_seed: null
# max_seq_len: 4096
# max_batch_size: 1
# - core_model_id: Llama-Guard-3-8B
# provider_id: meta-reference
# api: safety
# config:
# model: Llama-Guard-3-8B
# excluded_categories: []
# disable_input_check: false
# disable_output_check: false
# - core_model_id: Prompt-Guard-86M
# provider_id: meta-reference
# api: safety
# config:
# model: Prompt-Guard-86M