From b59a37fcf909a0fe29205dc025ed9316b05a154c Mon Sep 17 00:00:00 2001
From: Ratnopam Charabarti <ratnopamc@yahoo.com>
Date: Sun, 14 Jul 2024 21:43:42 -0700
Subject: [PATCH] fix: Fix Triton server model loading error (#584)

---
 ai-ml/nvidia-triton-server/nvidia-triton-server.tf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/ai-ml/nvidia-triton-server/nvidia-triton-server.tf b/ai-ml/nvidia-triton-server/nvidia-triton-server.tf
index e2a76eccf..e0a9fb1ec 100644
--- a/ai-ml/nvidia-triton-server/nvidia-triton-server.tf
+++ b/ai-ml/nvidia-triton-server/nvidia-triton-server.tf
@@ -53,11 +53,11 @@ module "triton_server_vllm" {
         limits:
           cpu: 10
           memory: 60Gi
-          nvidia.com/gpu: 1
+          nvidia.com/gpu: 4
         requests:
           cpu: 10
           memory: 60Gi
-          nvidia.com/gpu: 1
+          nvidia.com/gpu: 4
       nodeSelector:
         NodeGroupType: g5-gpu-karpenter
         type: karpenter