nvcc fatal : Unknown option '-extra-device-vectorization'

[bolongliu]

when I run following code:

import torch

from xlstm import (
    xLSTMBlockStack,
    xLSTMBlockStackConfig,
    mLSTMBlockConfig,
    mLSTMLayerConfig,
    sLSTMBlockConfig,
    sLSTMLayerConfig,
    FeedForwardConfig,
)

cfg = xLSTMBlockStackConfig(
    mlstm_block=mLSTMBlockConfig(
        mlstm=mLSTMLayerConfig(
            conv1d_kernel_size=4, qkv_proj_blocksize=4, num_heads=4
        )
    ),
    slstm_block=sLSTMBlockConfig(
        slstm=sLSTMLayerConfig(
            backend="cuda",
            num_heads=4,
            conv1d_kernel_size=4,
            bias_init="powerlaw_blockdependent",
        ),
        feedforward=FeedForwardConfig(proj_factor=1.3, act_fn="gelu"),
    ),
    context_length=256,
    num_blocks=7,
    embedding_dim=128,
    slstm_at=[1],

)

xlstm_stack = xLSTMBlockStack(cfg)

x = torch.randn(4, 256, 128).to("cuda")
xlstm_stack = xlstm_stack.to("cuda")
y = xlstm_stack(x)
y.shape == x.shape

it has error:nvcc fatal : Unknown option '-extra-device-vectorization'

How to solve it?

[kpoeppel]

Maybe you have an old version of nvcc? The setup via conda and the current environment yaml should work now.