From a2636842846676308c574f5b2e6f2616c5f535c6 Mon Sep 17 00:00:00 2001
From: Tyler Perkins <tyler@clortox.com>
Date: Sat, 30 Mar 2024 23:03:01 -0400
Subject: [PATCH] Upgrade version and use gpt2

---
 vllm/vllm-deployment.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/vllm/vllm-deployment.yaml b/vllm/vllm-deployment.yaml
index d5461cf..3c93a25 100644
--- a/vllm/vllm-deployment.yaml
+++ b/vllm/vllm-deployment.yaml
@@ -16,7 +16,7 @@ spec:
       runtimeClassName: nvidia
       containers:
         - name: vllm-inference-server
-          image: vllm/vllm-openai:v0.3.3
+          image: vllm/vllm-openai:latest
           imagePullPolicy: IfNotPresent
 
           resources:
@@ -33,7 +33,7 @@ spec:
                 #args:
                 #- while true; do sleep 2600; done
           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",
                  "--disable-log-requests",
                  "--trust-remote-code",