phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-22 22:49:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

openai mock server, Split of "k8s bench, locust"

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-08-11 16:34:50 -07:00
parent 78a59a4dbe
commit 9db924adae
11 changed files with 1234 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/source/distributions/k8s/stack-k8s.yaml.template
View file

@ -40,19 +40,19 @@ spec:
value: "3072"
- name: VLLM_SAFETY_URL
value: http://vllm-server-safety.default.svc.cluster.local:8001/v1
- name: VLLM_TLS_VERIFY
value: "false"
- name: POSTGRES_HOST
value: postgres-server.default.svc.cluster.local
- name: POSTGRES_PORT
value: "5432"
- name: VLLM_TLS_VERIFY
value: "false"
- name: INFERENCE_MODEL
value: "${INFERENCE_MODEL}"
- name: SAFETY_MODEL
value: "${SAFETY_MODEL}"
- name: TAVILY_SEARCH_API_KEY
value: "${TAVILY_SEARCH_API_KEY}"
command: ["python", "-m", "llama_stack.core.server.server", "--config", "/etc/config/stack_run_config.yaml", "--port", "8321"]
command: ["python", "-m", "llama_stack.core.server.server", "/etc/config/stack_run_config.yaml", "--port", "8321"]
ports:
- containerPort: 8321
volumeMounts: