Causal depthwise conv1d in CUDA with a PyTorch interface
Features:
- Support fp32, fp16, bf16.
- Kernel size 2, 3, 4.
How to use
from causal_conv1d import causal_conv1d_fn
def causal_conv1d_fn(x, weight, bias=None, activation=None):
"""
x: (batch, dim, seqlen)
weight: (dim, width)
bias: (dim,)
activation: either None or "silu" or "swish"
out: (batch, dim, seqlen)
"""
Equivalent to:
import torch.nn.functional as F
F.conv1d(x, weight.unsqueeze(1), bias, padding=width - 1, groups=dim)[..., :seqlen]
1 maintainer
Release files for causal-conv1d 1.2.0.post2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| causal_conv1d-1.2.0.post2.tar.gz | 7.1 kB | Details |
Release files / causal_conv1d-1.2.0.post2.tar.gz
| Download URL | causal_conv1d-1.2.0.post2.tar.gz |
|---|---|
| Size | 7.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3e35b96718b81a0b34c3717b5df06fd3ba44794079e40b34b719b152806acc1b
|
|
BLAKE2b-256 checksum How to use checksums |
7b02d2ff7b71358dadde5278b5a8c70b569124c64464a1f412469366fc639ac9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.10.13
|
