causal-conv1d

library1.6.1pypypiunverified

Causal depthwise 1D convolution CUDA kernel with PyTorch interface, commonly used as a building block for state-space models like Mamba. Current version: 1.6.1. Active development; breaking API changes between v1.x versions.

llm-agents ai-ml

pip install causal-conv1d

github ↗package ↗

INSTALL

IMPORT

SIG · CAUSAL-CONV1D

causal-conv1d

llm-agentspythonv1.6.1

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

causal_conv1d_fn

✓ from causal_conv1d import causal_conv1d_fn

✗ from causal_conv1d.causal_conv1d import causal_conv1d_fn

Not a submodule; direct import from package top-level.

CausalConv1dFn

✓ from causal_conv1d import CausalConv1dFn

✗ from causal_conv1d import CausalConv1d

CausalConv1d class never existed; use CausalConv1dFn.

Basic usage: apply causal depthwise conv1d on CUDA tensor.

import torch from causal_conv1d import causal_conv1d_fn x = torch.randn(2, 64, 128, device='cuda') weight = torch.randn(64, 3, device='cuda') # depthwise, kernel_size=3 bias = torch.randn(64, device='cuda') out = causal_conv1d_fn(x, weight, bias, activation='silu') print(out.shape) # torch.Size([2, 64, 128])

Debug

Known issues

breakingIn v1.4.0, the function signature changed: activation parameter must be passed as a string (e.g., 'silu') instead of None or torch.nn.SiLU. Also dims argument was removed.

fix

Update calls: use activation='silu' (or None) and remove dims from kwargs.

affects: >=1.4.0

gotchaThe kernel only supports CUDA. Passing CPU tensors will raise a RuntimeError. Always ensure inputs are on CUDA device.

fix

Move tensors to CUDA: x = x.cuda() before calling causal_conv1d_fn.

affects: all

gotchaWeight tensor must be 2D (out_channels, kernel_size) for depthwise convolution. Using 1D or transposed dimensions causes silent shape errors or kernel launch failures.

fix

Verify weight shape: weight.shape should be (C, K) where C is channels and K is kernel size (odd).

affects: all

deprecatedThe old import path causal_conv1d.causal_conv1d_interface is deprecated since v1.2.0. Use causal_conv1d directly.

fix

Change import to: from causal_conv1d import causal_conv1d_fn

affects: >=1.2.0

Upgrade

Version history

1.6.1latest on PyPI · released Mar 10, 2026

Audit

Dependencies

torchrequiredCore dependency; provides tensor types and CUDA support

Agent activity

29 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/Dao-AILab/causal-conv1d ↗

packagehttps://pypi.org/project/causal-conv1d/ ↗