62 lines
2.2 KiB
Python
62 lines
2.2 KiB
Python
import pytest
|
|
import torch
|
|
|
|
from tests.kernels.utils import opcheck
|
|
from vllm.model_executor.layers.layernorm import RMSNorm
|
|
from vllm.utils import seed_everything
|
|
|
|
DTYPES = [torch.half, torch.bfloat16, torch.float]
|
|
NUM_TOKENS = [7, 83, 4096] # Arbitrary values for testing
|
|
HIDDEN_SIZES = [768, 769, 770, 771, 5120, 5124, 5125, 5126, 8192,
|
|
8199] # Arbitrary values for testing
|
|
ADD_RESIDUAL = [False, True]
|
|
SEEDS = [0]
|
|
CUDA_DEVICES = [
|
|
f"cuda:{i}" for i in range(1 if torch.cuda.device_count() == 1 else 2)
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("num_tokens", NUM_TOKENS)
|
|
@pytest.mark.parametrize("hidden_size", HIDDEN_SIZES)
|
|
@pytest.mark.parametrize("add_residual", ADD_RESIDUAL)
|
|
@pytest.mark.parametrize("dtype", DTYPES)
|
|
@pytest.mark.parametrize("seed", SEEDS)
|
|
@pytest.mark.parametrize("device", CUDA_DEVICES)
|
|
@torch.inference_mode()
|
|
def test_rms_norm(
|
|
num_tokens: int,
|
|
hidden_size: int,
|
|
add_residual: bool,
|
|
dtype: torch.dtype,
|
|
seed: int,
|
|
device: str,
|
|
) -> None:
|
|
seed_everything(seed)
|
|
torch.set_default_device(device)
|
|
layer = RMSNorm(hidden_size).to(dtype=dtype)
|
|
layer.weight.data.normal_(mean=1.0, std=0.1)
|
|
scale = 1 / (2 * hidden_size)
|
|
x = torch.randn(num_tokens, hidden_size, dtype=dtype)
|
|
x *= scale
|
|
residual = torch.randn_like(x) * scale if add_residual else None
|
|
|
|
# NOTE(woosuk): The reference implementation should be executed first
|
|
# because the custom kernel is in-place.
|
|
ref_out = layer.forward_native(x, residual)
|
|
out = layer(x, residual)
|
|
# NOTE(woosuk): LayerNorm operators (including RMS) typically have larger
|
|
# numerical errors than other operators because they involve reductions.
|
|
# Therefore, we use a larger tolerance.
|
|
if add_residual:
|
|
torch.testing.assert_close(out[0], ref_out[0], atol=1e-2, rtol=1e-2)
|
|
torch.testing.assert_close(out[1], ref_out[1], atol=1e-2, rtol=1e-2)
|
|
else:
|
|
torch.testing.assert_close(out, ref_out, atol=1e-2, rtol=1e-2)
|
|
|
|
if residual is not None:
|
|
opcheck(torch.ops._C.fused_add_rms_norm,
|
|
(x, residual, layer.weight.data, layer.variance_epsilon))
|
|
else:
|
|
opcheck(torch.ops._C.rms_norm,
|
|
(out, x, layer.weight.data, layer.variance_epsilon))
|