Supported machines

Supported Machines

The fal runtime lets you specify the size of the machine that your fal functions run on. This is done using the machine_type argument in the fal.function decorator. Currently, the following following options are available:

XS0.25 CPU cores, 256MB RAM (default)
S0.50 CPU cores, 1GB RAM
M2 CPU cores, 8GB RAM
L4 CPU cores, 32GB RAM
GPU-T44 CPU cores, 26GB RAM, 1 GPU core (T4, 16 GB VRAM)
GPU8 CPU cores, 64GB RAM, 1 GPU core (A100, 40GB VRAM)

For example:

def my_function():

def my_other_function():

By default, the machine_type is set to XS.

You can also switch the machine type of an existing fal function by using the on method.

my_function_S = my_function.on(machine_type="S")

In the above example, my_function_S is a new fal function that has the same contents as my_function, but it will run on a machine type S.

Both functions can be called:

my_function() # executed on machine type `GPU`
my_function_S() # same as my_function but executed on machine type `S`

my_function is executed on machine type GPU. And my_function_S, which has the same logic as my_function, is now executed on machine type S.

2023 © Features and Labels Inc.