phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-08 06:44:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

play around with util

Browse source
This commit is contained in:
Ashwin Bharambe 2025-06-01 15:34:43 -07:00
parent a36b0c5fe3
commit d93f6c9e5b
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/source/distributions/k8s/stack-k8s.yaml.template
View file

@ -27,7 +27,7 @@ spec:
containers:
- name: llama-stack
image: llamastack/distribution-remote-vllm:latest
imagePullPolicy: IfNotPresent
imagePullPolicy: Always # since we have specified latest instead of a version
env:
- name: VLLM_URL
value: http://vllm-server.default.svc.cluster.local:8000/v1

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

@ -32,7 +32,7 @@ spec:
image: vllm/vllm-openai:latest
command: ["/bin/sh", "-c"]
args:
- "vllm serve ${INFERENCE_MODEL} --dtype float16 --enforce-eager --max-model-len 8192 --gpu-memory-utilization 0.5"
- "vllm serve ${INFERENCE_MODEL} --dtype float16 --enforce-eager --max-model-len 6144 --gpu-memory-utilization 0.55"
env:
- name: HUGGING_FACE_HUB_TOKEN
valueFrom:
@ -81,7 +81,7 @@ spec:
image: vllm/vllm-openai:latest
command: ["/bin/sh", "-c"]
args: [
"vllm serve ${SAFETY_MODEL} --dtype float16 --enforce-eager --max-model-len 8192 --gpu-memory-utilization 0.3"
"vllm serve ${SAFETY_MODEL} --dtype float16 --enforce-eager --max-model-len 6144 --gpu-memory-utilization 0.28"
]
env:
- name: HUGGING_FACE_HUB_TOKEN