[FEAT] Terraform Quickstart Tutorials for Google GKE (#250)

* complete guide with gke terraform

Signed-off-by: falconlee236 <[email protected]>

* finish lint and proudction-stack gke terrafom support

Signed-off-by: falconlee236 <[email protected]>

* add observlity stack

Signed-off-by: falconlee236 <[email protected]>

* add variable with gpu node pool settings

Signed-off-by: falconlee236 <[email protected]>

* add gpu variable and machine variable to customize node resource

Signed-off-by: falconlee236 <[email protected]>

* add add in the Readme about choosing the GPUs I want to use in the beginning or the model I want to deploy

Signed-off-by: falconlee236 <[email protected]>

---------

Signed-off-by: falconlee236 <[email protected]>

Author: falconlee236

.gitignore

@@ -99,3 +99,46 @@ helm/examples
 src/vllm_router/_version.py
 
 /tutorials/assets/private.yaml
+
+
+# terraform
+# Local .terraform directories
+**/.terraform/*
+
+# .tfstate files
+*.tfstate
+*.tfstate.*
+
+# Crash log files
+crash.log
+crash.*.log
+
+# Exclude all .tfvars files, which are likely to contain sensitive data, such as
+# password, private keys, and other secrets. These should not be part of version
+# control as they are data points which are potentially sensitive and subject
+# to change depending on the environment.
+*.tfvars
+*.tfvars.json
+
+# Ignore override files as they are usually used to override resources locally and so
+# are not checked in
+override.tf
+override.tf.json
+*_override.tf
+*_override.tf.json
+
+# Ignore transient lock info files created by terraform apply
+.terraform.tfstate.lock.info
+
+# Include override files you do wish to add to version control using negated pattern
+# !example_override.tf
+
+# Include tfplan files to ignore the plan output of command: terraform plan -out=tfplan
+# example: *tfplan*
+
+# Ignore CLI configuration files
+.terraformrc
+terraform.rc
+
+# google cloud platform
+credentials.json

tutorials/terraform/gke/Makefile

@@ -0,0 +1,43 @@
+RED = $(shell tput -Txterm setab 1 && tput -Txterm setaf 0)
+GREEN = $(shell tput -Txterm setab 2 && tput -Txterm setaf 0)
+PURPLE = $(shell tput -Txterm setab 5 && tput -Txterm setaf 7)
+RESET = $(shell tput -Txterm sgr0)
+CLUSTER_NAME = production-stack
+REGION = us-central1-a
+
+
+all: create
+
+create: create-gke-infra create-helm-chart
+
+create-gke-infra:
+	@echo ""
+	@echo "$(GREEN) create gke infra $(RESET)"
+	@cd gke-infrastructure && terraform init
+	@cd gke-infrastructure && terraform apply -auto-approve
+
+create-helm-chart:
+	@echo ""
+	@echo "$(GREEN) create helm chart $(RESET)"
+	gcloud container clusters get-credentials $(CLUSTER_NAME) --region=$(REGION)
+	@cd production-stack && terraform init
+	@cd production-stack && terraform apply -auto-approve
+
+
+destroy-gke-infra:
+	@echo ""
+	@echo "$(PURPLE) destroy gke infra $(RESET)"
+	@cd gke-infrastructure && terraform init
+	@cd gke-infrastructure && terraform destroy -auto-approve
+
+destroy-helm-chart:
+	@echo ""
+	@echo "$(PURPLE) destroy helm chart $(RESET)"
+	@cd production-stack && terraform init
+	@cd production-stack && terraform destroy -auto-approve
+
+clean: destroy-helm-chart
+
+fclean: destroy-helm-chart destroy-gke-infra
+
+.PHONY: all create init clean fclean