phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

second try

Browse source
This commit is contained in:
Kai Wu 2025-07-30 14:51:43 -07:00
parent 31a15332c4
commit 1cb9d3bca2
11 changed files with 237 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

17
docs/source/distributions/k8s/stack_run_config.yaml
View file

@ -16,13 +16,12 @@ providers:
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
- provider_id: vllm-safety
provider_type: remote::vllm
- provider_id: nvidia
provider_type: remote::nvidia
config:
url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
url: ${env.NVIDIA_BASE_URL:=http://localhost:8001/v1}
api_key: ${env.NVIDIA_API_KEY:=}
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -103,11 +102,9 @@ models:
provider_id: vllm-inference
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
provider_id: vllm-safety
model_id: ${env.CODE_MODEL:=bigcode/starcoder2-7b}
provider_id: nvidia
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
vector_dbs: []
datasets: []
scoring_fns: []