MaxDiffusion inference on v6e TPUs

This tutorial shows how to serve MaxDiffusion models on TPU v6e. In this tutorial, you generate images using the Stable Diffusion XL model.

Note: After you complete the inference benchmark, be sure to clean up the TPU resources.

Before you begin

Prepare to provision a TPU v6e with 4 chips:

1. Sign in to your Google Account. If you haven't already, sign up for a new account.
2. In the Google Cloud console, select or create a Google Cloud project from the project selector page.
3. Enable billing for your Google Cloud project. Billing is required for all Google Cloud usage.
4. Install the gcloud alpha components.

5. Run the following command to install the latest version of gcloudcomponents.

   gcloud components update
   

6. Enable the TPU API through the following gcloud command using Cloud Shell. You can also enable it from the Google Cloud console.

   gcloud services enable tpu.googleapis.com
   

7. Create a service identity for the TPU VM.

   gcloud alpha compute tpus tpu-vm service-identity create --zone=ZONE

8. Create a TPU service account and grant access to Google Cloud services.

   Service accounts allow the Google Cloud TPU service to access other Google Cloud services. A user-managed service account is recommended. Follow these guides to create and grant roles. The following roles are necessary:

   • TPU Admin: Needed to create a TPU
   • Storage Admin: Needed for accessing Cloud Storage
   • Logs Writer: Needed for writing logs with the Logging API
   • Monitoring Metric Writer: Needed for writing metrics to Cloud Monitoring

9. Authenticate with Google Cloud and configure the default project and zone for Google Cloud CLI.

   gcloud auth login
   gcloud config set project PROJECT_ID
   gcloud config set compute/zone ZONE

Secure capacity

Contact your Cloud TPU sales or account team to request TPU quota and to ask any questions about capacity.

Provision the Cloud TPU environment

You can provision v6e TPUs with GKE, with GKE and XPK, or as queued resources.

Note: This document describes how to provision TPUs using queued resources. If you are provisioning your TPUs using XPK (a wrapper CLI tool over GKE), set up XPK permissions on your user account for GKE.

Prerequisites

• Verify that your project has enough TPUS_PER_TPU_FAMILY quota, which specifies the maximum number of chips you can access within your Google Cloud project.
• This tutorial was tested with the following configuration:
  • Python 3.10 or later
  • Nightly software versions:
    • nightly JAX 0.4.32.dev20240912
    • nightly LibTPU 0.1.dev20240912+nightly
  • Stable software versions:
    • JAX + JAX Lib of v0.4.35
• Verify that your project has enough TPU quota for:
  • TPU VM quota
  • IP Address quota
  • Hyperdisk balanced quota
• User project permissions
  • If you are using GKE with XPK, see Cloud Console Permissions on the user or service account for the permissions needed to run XPK.

Provision a TPU v6e

   gcloud alpha compute tpus queued-resources create QUEUED_RESOURCE_ID \
        --node-id TPU_NAME \
        --project PROJECT_ID \
        --zone ZONE \
        --accelerator-type v6e-4 \
        --runtime-version v2-alpha-tpuv6e \
        --service-account SERVICE_ACCOUNT

Use the list or describe commands to query the status of your queued resource.

   gcloud alpha compute tpus queued-resources describe ${QUEUED_RESOURCE_ID}  \
      --project ${PROJECT_ID} --zone ${ZONE}

For a complete list of queued resource request statuses, see the Queued Resources documentation.

Connect to the TPU using SSH

   gcloud compute tpus tpu-vm ssh TPU_NAME

Create a Conda environment

1. Create a directory for Miniconda:

   mkdir -p ~/miniconda3

2. Download the Miniconda installer script:

   wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh

3. Install Miniconda:

   bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3

4. Remove the Miniconda installer script:

   rm -rf ~/miniconda3/miniconda.sh

5. Add Miniconda to your PATH variable:

   export PATH="$HOME/miniconda3/bin:$PATH"

6. Reload ~/.bashrc to apply the changes to the PATH variable:

   source ~/.bashrc

7. Create a new Conda environment:

   conda create -n tpu python=3.10

8. Activate the Conda environment:

   source activate tpu

Set up MaxDiffusion

1. Clone the MaxDiffusion repository and navigate to the MaxDiffusion directory:

   git clone https://github.com/google/maxdiffusion.git && cd maxdiffusion

2. Switch to the mlperf-4.1 branch:

   git checkout mlperf4.1

3. Install MaxDiffusion:

   pip install -e .

4. Install dependencies:

   pip install -r requirements.txt

5. Install JAX:

   pip install -U --pre jax[tpu] -f https://storage.googleapis.com/jax-releases/jax_nightly_releases.html -f https://storage.googleapis.com/jax-releases/libtpu_releases.html

6. Install additional dependencies:

    pip install huggingface_hub==0.25 absl-py flax tensorboardX google-cloud-storage torch tensorflow transformers 

Generate images

1. Set environment variables to configure the TPU runtime:

   LIBTPU_INIT_ARGS="--xla_tpu_rwb_fusion=false --xla_tpu_dot_dot_fusion_duplicated=true --xla_tpu_scoped_vmem_limit_kib=65536"

2. Generate images using the prompt and configurations defined in src/maxdiffusion/configs/base_xl.yml:

   python -m src.maxdiffusion.generate_sdxl src/maxdiffusion/configs/base_xl.yml run_name="my_run"

   When the images have been generated, be sure to clean up the TPU resources.

Clean up

Delete the TPU:

gcloud compute tpus queued-resources delete QUEUED_RESOURCE_ID \
    --project PROJECT_ID \
    --zone ZONE \
    --force \
    --async