Infrastructure/Gluttony-Cluster
2
1
Fork 0
Code Issues 13 Pull Requests Wiki Activity

Upgrade version and use gpt2
All checks were successful
continuous-integration/drone/push Build is passing
Details

Browse Source
This commit is contained in:
Tyler Perkins 2024-03-30 23:03:01 -04:00
parent 5ca94dda0b
commit a263684284
Signed by: tyler
GPG Key ID: 03B27509E17EFDC8
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/vllm-deployment.yaml
View File

@ -16,7 +16,7 @@ spec:
runtimeClassName: nvidia runtimeClassName: nvidia
containers: containers:
- name: vllm-inference-server - name: vllm-inference-server
image: vllm/vllm-openai:v0.3.3 image: vllm/vllm-openai:latest
imagePullPolicy: IfNotPresent imagePullPolicy: IfNotPresent
resources: resources:
@ -33,7 +33,7 @@ spec:
#args: #args:
#- while true; do sleep 2600; done #- while true; do sleep 2600; done
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
args: ["--model=mistralai/Mistral-7B-v0.1", args: ["--model=openai-community/gpt2",
"--gpu-memory-utilization=0.95", "--gpu-memory-utilization=0.95",
"--disable-log-requests", "--disable-log-requests",
"--trust-remote-code", "--trust-remote-code",