diff --git a/examples/gcp-linux-fastchat-new-vs-old/README.md b/examples/gcp-linux-fastchat-new-vs-old/README.md deleted file mode 100644 index 170df5e..0000000 --- a/examples/gcp-linux-fastchat-new-vs-old/README.md +++ /dev/null @@ -1,62 +0,0 @@ -

- Intel Logo -

- -# Intel Optimized Cloud Modules for Terraform - -© Copyright 2024, Intel Corporation - -## GCP C3 4th Gen Xeon(code named Sapphire Rapids) & Intel® Cloud Optimized Recipe for FastChat - -This demo will showcase Large Language Model(LLM) CPU inference using 4th Gen Xeon Scalable Processors on GCP. - -## Usage - -You may need to change the appropriate IAM settings as described here: https://cloud.google.com/docs/terraform/get-started-with-terraform - -1. Log on to CGP Portal -2. Enter the GCP Cloud Shell (terminal button on top right of page) -3. Run the following commands in order: - -`git clone https://github.com/intel/terraform-intel-gcp-vm.git` - -`cd terraform-intel-gcp-vm/examples/gcp-linux-fastchat-new-vs-old` - -`terraform init` - -`terraform apply` - -## Running the Demo - - -1. **Wait ~10 minutes** for the Recipe to download/install FastChat and the LLM model before continuing -2. SSH into newly created GCP VM -3. **Run `source /usr/local/bin/run_demo.sh`** -4. If you did not choose to open a port, your app will be proxied through gradio. See https://xxxxxxx.gradio.live URL that is generated during the gradio run. -5. Otherwise, if you choose to open port 7860 in main.tf: on your computer, open a browser and navigate to **http://:7860**. Get your Public IP from the "Compute Engine" section of the GCP console. - -

- Gradio_Output -

- - ---- KNOWN ISSUE --- - -The demo may initially fail. In this case, run - -`pip install gradio==3.10` - -`pip install gradio==3.35.2` - -Then, run: - -`source /usr/local/bin/run_demo.sh` - -And navigate again using your browser. - -## Pre-requisites for running on a Workstation (bypass if using GCP Cloud Shell) - -1. Google Cloud CLI: https://cloud.google.com/sdk/docs/install -2. CGP account access configured: https://registry.terraform.io/providers/hashicorp/google/latest/docs/guides/provider_reference.html#running-terraform-on-your-workstation -3. Terraform: https://learn.hashicorp.com/tutorials/terraform/install-cli -4. Git: https://git-scm.com/book/en/v2/Getting-Started-Installing-Git \ No newline at end of file diff --git a/examples/gcp-linux-fastchat-new-vs-old/cloud_init.yml b/examples/gcp-linux-fastchat-new-vs-old/cloud_init.yml deleted file mode 100644 index c203173..0000000 --- a/examples/gcp-linux-fastchat-new-vs-old/cloud_init.yml +++ /dev/null @@ -1,15 +0,0 @@ -#cloud-config -package_update: true -package_upgrade: true - -package: - - git - -ansible: - install_method: distro - package_name: ansible - pull: - url: "https://github.com/intel/optimized-cloud-recipes.git" - playbook_name: "recipes/ai-fastchat-amx-ubuntu/recipe.yml" - - diff --git a/examples/gcp-linux-fastchat-new-vs-old/main.tf b/examples/gcp-linux-fastchat-new-vs-old/main.tf deleted file mode 100644 index fa43760..0000000 --- a/examples/gcp-linux-fastchat-new-vs-old/main.tf +++ /dev/null @@ -1,58 +0,0 @@ -variable "project" { - type = string - description = "GCP Project ID" -} - - -#GCP Linux VM with Intel Cloud Optimized Recipe for FastChat -module "linux_vm" { - source = "intel/gcp-vm/intel" - project = var.project - boot_image_project = "ubuntu-os-cloud" - boot_image_family = "ubuntu-2204-lts" - name = "spr-intel-fastchat-vm" - zone = "us-central1-a" - machine_type = "c3-standard-22" - tags = ["fschat"] - user_data = templatefile("./cloud_init.yml", {}) - access_config = [{ - nat_ip = null - public_ptr_domain_name = null - network_tier = "PREMIUM" - }, ] -} - -#GCP Linux VM with Intel Cloud Optimized Recipe for FastChat -module "linux_vm2" { - source = "intel/gcp-vm/intel" - project = var.project - boot_image_project = "ubuntu-os-cloud" - boot_image_family = "ubuntu-2204-lts" - name = "older-intel-fastchat-vm" - zone = "us-central1-a" - machine_type = "custom-22-90112" - allow_stopping_for_update = true - tags = ["fschat"] - user_data = templatefile("./cloud_init.yml", {}) - access_config = [{ - nat_ip = null - public_ptr_domain_name = null - network_tier = "PREMIUM" - }, ] -} - -#FastChat Gradio Webserver can be accessed by the Gradio Proxy. See https://xxxxxxx.gradio.live URL that is generated during the gradio run -#You can also access it directly on the VM Public IP on Port 7860, http://:7860 -resource "google_compute_firewall" "rules" { - project = var.project - name = "fastchat-firewall" - network = "default" - description = "Allows access to FastChat Webserver." - - allow { - protocol = "tcp" - ports = ["7860"] - } - source_ranges = [ "0.0.0.0/0" ] - target_tags = ["fschat"] -} diff --git a/examples/gcp-linux-fastchat/README.md b/examples/gcp-linux-fastchat/README.md deleted file mode 100644 index 8eba7db..0000000 --- a/examples/gcp-linux-fastchat/README.md +++ /dev/null @@ -1,56 +0,0 @@ -

- Intel Logo -

-# Intel Optimized Cloud Modules for Terraform - -© Copyright 2024, Intel Corporation - -## GCP C3 4th Gen Xeon(codenamed Sapphire Rapids) + Cloud Optimized Recipe for FasChat - -This demo will demonstrate the 1.3x speedup in Large Language Model CPU inference from 3rd gen Xeon to 4th gen Xeon - -## Pre-requisites - -1. Install Terraform: https://learn.hashicorp.com/tutorials/terraform/install-cli -2. Install Git: https://git-scm.com/book/en/v2/Getting-Started-Installing-Git - -## Usage - -You may need to change the appropriate IAM settings as described here: https://cloud.google.com/docs/terraform/get-started-with-terraform - -Next, enter the cloud shell in GCP (terminal button on top right of page) - -Run the following commands in order: - -`git clone https://github.com/intel/terraform-intel-gcp-vm.git` - -`cd terraform-intel-gcp-vm/examples/gcp-linux-fastchat` - -`terraform init` - -`terraform apply` - -## Running the Demo - -**NOTE: This demo requires port 7860 to be open.** If you are running this on GCP, you will need to open this port in the GCP Firewall Policies. If you are running this on AWS, you will need to open this port in the AWS security group. - -**1-SSH into newly created GCP VM and run `source /usr/local/bin/run_demo.sh`** - -**2-On your computer open a browser and navigate to http://:7860** - - ---- KNOWN ISSUE --- - -This may fail. In this case, run - -`pip install gradio==3.10` - -`pip install gradio==3.35.2` - -Then, run: - -`source /usr/local/bin/run_demo.sh` - -and navigate to http://:7860 on your computer. - - diff --git a/examples/gcp-linux-fastchat/cloud_init.yml b/examples/gcp-linux-fastchat/cloud_init.yml deleted file mode 100644 index c203173..0000000 --- a/examples/gcp-linux-fastchat/cloud_init.yml +++ /dev/null @@ -1,15 +0,0 @@ -#cloud-config -package_update: true -package_upgrade: true - -package: - - git - -ansible: - install_method: distro - package_name: ansible - pull: - url: "https://github.com/intel/optimized-cloud-recipes.git" - playbook_name: "recipes/ai-fastchat-amx-ubuntu/recipe.yml" - - diff --git a/examples/gcp-linux-fastchat/cloud_init_worker.yml b/examples/gcp-linux-fastchat/cloud_init_worker.yml deleted file mode 100644 index 5d6ef6a..0000000 --- a/examples/gcp-linux-fastchat/cloud_init_worker.yml +++ /dev/null @@ -1,15 +0,0 @@ -#cloud-config -package_update: true -package_upgrade: true - -package: - - git - -ansible: - install_method: distro - package_name: ansible - pull: - url: "https://github.com/intel/optimized-cloud-recipes.git" - playbook_name: "recipes/ai-fastchat-amx-ubuntu/recipe-worker.yml" - extra-vars: "controller_ip=${controller_ip} worker_ip=${worker_ip}" - diff --git a/examples/gcp-linux-fastchat/main.tf b/examples/gcp-linux-fastchat/main.tf deleted file mode 100644 index 9bc69e3..0000000 --- a/examples/gcp-linux-fastchat/main.tf +++ /dev/null @@ -1,85 +0,0 @@ -variable "project" { - type = string - description = "project_id" - default = "intel-csa-resource-gcp" -} - -variable "controller_ip" { - type = string - description = "IP of controller node" - default = "10.128.15.213" -} - -variable "worker_ip" { - type = string - description = "IP of worker node" - default = "10.128.15.214" - -} - -module "linux_vm" { - source = "intel/gcp-vm/intel" - project = var.project - boot_image_project = "ubuntu-os-cloud" - boot_image_family = "ubuntu-2204-lts" - name = "intel-fastchat-test" - zone = "us-central1-a" - machine_type = "c3-highcpu-44" - network_ip = "10.128.15.213" - tags = ["fschat"] - user_data = templatefile("./cloud_init.yml", {}) - access_config = [{ - nat_ip = null - public_ptr_domain_name = null - network_tier = "PREMIUM" - }, ] -} - -module "linux_vm_worker" { - source = "intel/gcp-vm/intel" - project = var.project - boot_image_project = "ubuntu-os-cloud" - boot_image_family = "ubuntu-2204-lts" - name = "intel-fastchat-older-node" - zone = "us-central1-a" - machine_type = "custom-44-90112" - network_ip = "10.128.15.214" - tags = ["fschat"] - user_data = templatefile("./cloud_init_worker.yml", { controller_ip = var.controller_ip, worker_ip = var.worker_ip }) - access_config = [{ - nat_ip = null - public_ptr_domain_name = null - network_tier = "PREMIUM" - }, ] -} - -resource "google_compute_firewall" "rules-1" { - project = var.project - name = "fastchat-firewall" - network = "default" - description = "Allows fastchat VMs to communicate" - - allow { - protocol = "tcp" - ports = ["21000-21020"] - } - - source_tags = ["fschat"] - target_tags = ["fschat"] -} - -# Port 7860 is required to access the FastChat Webserver without proxying through gradio. Disabled by default. -resource "google_compute_firewall" "rules-2" { - project = var.project - name = "fastchat-firewall-public-access" - network = "default" - description = "Allows access to FastChat Webserver." - disabled = true # Remove this line or set to false to open up the webserver to traffic from port 7860 - - allow { - protocol = "tcp" - ports = ["7860"] - } - source_ranges = [ "0.0.0.0/0" ] - target_tags = ["fschat"] -}