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

first draft

Browse source
This commit is contained in:
Kai Wu 2025-07-25 10:41:06 -07:00
parent 025163d8e6
commit e614241876
9 changed files with 64 additions and 60 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/source/distributions/k8s/vllm-safety-k8s.yaml.template
View file

@ -25,14 +25,12 @@ spec:
app.kubernetes.io/name: vllm-safety
workload-type: inference
spec:
nodeSelector:
eks.amazonaws.com/nodegroup: gpu
containers:
- name: vllm-safety
image: vllm/vllm-openai:latest
command: ["/bin/sh", "-c"]
args: [
"vllm serve ${SAFETY_MODEL} --dtype float16 --enforce-eager --max-model-len 4096 --port 8001 --gpu-memory-utilization 0.3"
"vllm serve ${SAFETY_MODEL} --dtype float16 --enforce-eager --max-model-len 4096 --port 8001 --gpu-memory-utilization 0.6"
]
env:
- name: SAFETY_MODEL