Question regarding setting the RAM disk for MSA compute

sky1ove commented 7 hours ago

Besides the example of setting this gpu instance,

> gcloud compute instances create alphafold3
> --machine-type a2-ultragpu-1g
> --zone us-central1-a
> --image-family ubuntu-2204-lts
> --image-project ubuntu-os-cloud
> --maintenance-policy TERMINATE
> --boot-disk-size 1000
> --boot-disk-type pd-balanced

Could you show an example of setting a RAM disk from google cloud for the specific task of computing MSA?

Augustin-Zidek commented 7 hours ago

Please refer to https://github.com/google-deepmind/alphafold3/blob/main/docs/installation.md#obtaining-genetic-databases, in particular the section about using the gcp_mount_ssd.sh and copy_to_ssd.sh scripts.

Once you run those scripts to copy the relevant dbs in the SSD, you will have to launch as:

docker run -it \
    --volume $HOME/af_input:/root/af_input \
    --volume $HOME/af_output:/root/af_output \
    --volume <MODEL_PARAMETERS_DIR>:/root/models \
    --volume <SSD_DB_DIR>:/root/public_databases \
    --volume <DB_DIR>:/root/public_databases_fallback \
    --gpus all \
    alphafold3 \
    python run_alphafold.py \
    --json_path=/root/af_input/fold_input.json \
    --model_dir=/root/models \
    --db_dir=/root/public_databases \
    --db_dir=/root/public_databases_fallback \
    --output_dir=/root/af_output

sky1ove commented 5 hours ago

If I simply want a SSD / RAM-disk without GPU to run the MSA, which machine type from GCP do you recommend?

google-deepmind / alphafold3

Question regarding setting the RAM disk for MSA compute #176