Skip to content

Releases: Khushiyant/tether

v0.2.0

29 Dec 12:58

Choose a tag to compare

v0.2.0 (2025-12-29)

Chores

  • Add comprehensive benchmark suite for Tether, snnTorch, and SpikingJelly frameworks (f401fda)

  • Add comprehensive benchmark suite for Tether, snnTorch, and SpikingJelly frameworks (70eb398)

  • Add SpikingCIFARModel and TetherLM for CIFAR-10 training, include dataset download functionality, and update dependencies in pyproject.toml (8d3144c)

  • Refactor PLIF and LIF modules for improved readability and performance (26846fc)

  • Enhanced the PLIF and LIF classes by restructuring the initialization parameters for better clarity.

  • Updated the forward methods in both classes to improve code readability and maintainability.

  • Added support for vectorized decay and threshold parameters in PLIF.

  • Improved the handling of surrogate gradients in both LIF and PLIF.

  • Refactored the attention mechanism in SpikingSelfAttention to streamline operations.

  • Updated the Monitor utility to enhance voltage trace monitoring capabilities.

  • Added comprehensive tests for new features and ensured backward compatibility.

  • Cleaned up code formatting across multiple files for consistency.

  • Remove obsolete documentation files for tether modules (ae7b023)

  • Simplify spike handling in SNNTorch models and reset hidden states in MNIST model (70f4a42)

Features

  • Implement Triton kernels for causal linear attention and rate encoding, optimize LinearLIF layer (669912f)

Detailed Changes: v0.1.1...v0.2.0

v0.1.1

25 Dec 21:54

Choose a tag to compare

v0.1.1 (2025-12-25)

Bug Fixes

  • Enhance LIF and PLIF implementations with detailed documentation, improve Triton kernels, and update workflow for semantic release (99c7532)

Detailed Changes: v0.1.0...v0.1.1

v0.1.0

25 Dec 21:44

Choose a tag to compare

v0.1.0 (2025-12-25)

Chores

  • Add Sphinx documentation setup and update dependencies in pyproject.toml (4e77841)

  • Correct package path in wheel build configuration (2ba9444)

  • Enhance documentation, add new encoding utilities, and improve LIF functionality with surrogate gradients (daf68ab)

  • Remove test workflow from GitHub Actions (67f52af)

  • Rename job from 'build-and-deploy' to 'build' in GitHub Actions workflow (2e43c26)

  • Reorganize GitHub Actions test workflow and remove CHANGELOG file (4ef708e)

  • Update project description in pyproject.toml (758268b)

  • Update project name in pyproject.toml and streamline dependencies formatting (77bedba)

  • Update Sphinx documentation build paths and fix directory structure (e022cae)

  • Update Sphinx documentation build process and dependencies in pyproject.toml (777b38b)

Features

  • Implement ALIF and PLIF modules with Triton kernels, add surrogate gradient classes, and enhance benchmark functionality (042f891)

Detailed Changes: v0.0.1...v0.1.0

v0.0.1

25 Dec 12:28

Choose a tag to compare

v0.0.1 (2025-12-25)

Bug Fixes

  • Define shape variables in forward method of SpikingSelfAttention class (c7e15a7)

Chores

  • Add GitHub Actions for semantic release and testing (5a12ca2)

  • Add GitHub Actions workflow for testing with multiple Python versions (6334c5d)

  • Add GitHub Actions workflows for semantic release and testing with multiple Python versions (19ee3fc)

  • Add initial CHANGELOG file (ad53c31)

  • Downgrade Python version to 3.10 and simplify dependencies in pyproject.toml (9eb2844)

  • Initial commit (1a7d8f2)

  • Update GitHub Actions workflow to use 'uv' for Python setup and dependency management (d29f398)