petals/tests/test_aux_functions.py
Max Ryabinin 793726b041
Speed up loading blocks using init with meta weights (#285)
* Init WrappedBloomBlock with meta weights

---------

Co-authored-by: Alexander Borzunov <borzunov.alexander@gmail.com>
2023-03-13 00:49:04 +03:00

23 lines
731 B
Python

import pytest
import torch
from petals.client import DistributedBloomConfig
from petals.server.throughput import measure_compute_rps
from test_utils import MODEL_NAME
@pytest.mark.forked
@pytest.mark.parametrize("tensor_parallel", [False, True])
def test_compute_throughput(tensor_parallel: bool):
config = DistributedBloomConfig.from_pretrained(MODEL_NAME)
tensor_parallel_devices = ("cpu", "cpu") if tensor_parallel else ()
compute_rps = measure_compute_rps(
config,
device=torch.device("cpu"),
dtype=torch.bfloat16,
load_in_8bit=False,
tensor_parallel_devices=tensor_parallel_devices,
n_steps=10,
)
assert isinstance(compute_rps, float) and compute_rps > 0