Accelerate your Sieve functions with GPU.
gpu
parameter to your function decorator with the GPU you want. Today, Sieve offers a couple machine configurations listed below.
Name | GPU | Memory (GB) | vCPUs | Parameter |
---|---|---|---|---|
T4 (default) | T4 | 16 | 4 | sieve.gpu.T4() |
A100-40GB | A100-40GB | 85 | 12 | sieve.gpu.A100() |
A100-20GB | A100-20GB | 42.5 | 6 | sieve.gpu.A10020GB() |
V100 | V100 | 16 | 4 | sieve.gpu.V100() |
L4 | L4 | 32 | 8 | sieve.gpu.L4() |
cuda_version
parameter in the function decorator. The full list of possible CUDA versions can be found here.
split
argument in the GPU constructor to tell Sieve to let multiple workers share the same GPU. For example, the following would tell sieve to allocate 3 workers per GPU:
split
can be any integer between 1 and 8. Sieve will only share a GPU with other workers of the same function. Since split
number of workers share the same GPU, Sieve will spin up that many workers at a time.
Each shared worker will be billed at 1/split
the rate of a regular worker. So, Sieve will charge you the same amount per GPU hour regardless of how many workers are running on it.
Read more about the way the gpu
field works in SDK reference.
Let’s first create a new directory and set up our project.
Now, we can setup our YOLO model and write our inference code.
Finally, let's deploy our function to Sieve.
sieve_yolov8
directory, we can simply run:Run jobs!
sieve.gpu.T4(split=4)
.