fix: For issue 429 "Unable to deploy llama2 on Eks/Ray Serve/inf2" (#430

)
awslabs · Feb 26, 2024 · 30c5387 · 30c5387
1 parent 91154ef
commit 30c5387
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/.gitignore b/.gitignore
@@ -51,3 +51,7 @@ site
 .tfsec
 
 examples/gradio-ui/*
+ai-ml/trainium-inferentia/examples/gradio-ui/gradio_cached_examples/*
+
+# venv
+**/.venv/*
diff --git a/ai-ml/trainium-inferentia/eks.tf b/ai-ml/trainium-inferentia/eks.tf
@@ -116,7 +116,7 @@ module "eks" {
       max_size     = 8
       desired_size = 3
 
-      instance_types = ["m5.xlarge"]
+      instance_types = ["m5.2xlarge"]
 
       labels = {
         WorkerType    = "ON_DEMAND"