From e11ebcfb792570efa96078880c0dc2d369e4c418 Mon Sep 17 00:00:00 2001
From: Sam Stoelinga <sammiestoel@gmail.com>
Date: Sat, 2 Nov 2024 08:56:03 -0700
Subject: [PATCH] run make manifests

---
 manifests/models/llama-3.1-70b-instruct-awq-int4-gh200.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/manifests/models/llama-3.1-70b-instruct-awq-int4-gh200.yaml b/manifests/models/llama-3.1-70b-instruct-awq-int4-gh200.yaml
index 5c595d7d..dd2ef872 100644
--- a/manifests/models/llama-3.1-70b-instruct-awq-int4-gh200.yaml
+++ b/manifests/models/llama-3.1-70b-instruct-awq-int4-gh200.yaml
@@ -1,3 +1,4 @@
+# Source: models/templates/models.yaml
 apiVersion: kubeai.org/v1
 kind: Model
 metadata:
@@ -13,5 +14,4 @@ spec:
     - --enable-prefix-caching
     - --disable-log-requests
   targetRequests: 50
-  minReplicas: 1
-  resourceProfile: nvidia-gpu-gh200:1
\ No newline at end of file
+  resourceProfile: nvidia-gpu-gh200:1