sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update a100-vllm.yaml

Browse source
This commit is contained in:
sirius0xdev 2026-04-22 23:56:27 -04:00 • committed by GitHub
parent 77e8adf7b7
commit 5d108035db
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
apps/base/customer1/openclaw/a100-vllm.yaml
View file

@ -32,7 +32,7 @@ spec:
- name: TOKENIZER_MODE - name: TOKENIZER_MODE
value: "hf" value: "hf"
args: args:
- --model=llmfan46/Qwen3.5-27B-uncensored-heretic - --model=Youssofal/Qwen3.6-27B-Abliterated-Heretic-Uncensored-BF16
- --host=0.0.0.0 - --host=0.0.0.0
- --port=8000 - --port=8000
- --tensor-parallel-size=1 - --tensor-parallel-size=1
@ -53,11 +53,11 @@ spec:
resources: resources:
limits: limits:
nvidia.com/gpu: 1 nvidia.com/gpu: 1
memory: "80Gi" memory: "100Gi"
cpu: "16" cpu: "16"
requests: requests:
nvidia.com/gpu: 1 nvidia.com/gpu: 1
memory: "60Gi" memory: "80Gi"
cpu: "8" cpu: "8"
volumeMounts: volumeMounts:
- name: model-cache - name: model-cache
@ -65,12 +65,12 @@ spec:
volumes: volumes:
- name: model-cache - name: model-cache
persistentVolumeClaim: persistentVolumeClaim:
claimName: vllm-model-qwen3.5-27b-uncensored claimName: vllm-model-qwen3.6-27b-uncensored
--- ---
apiVersion: v1 apiVersion: v1
kind: PersistentVolumeClaim kind: PersistentVolumeClaim
metadata: metadata:
name: vllm-model-qwen3.5-27b-uncensored name: vllm-model-qwen3.6-27b-uncensored
namespace: customer1 namespace: customer1
spec: spec:
accessModes: accessModes: