Documentation History

This page records documentation changes by release.

For runtime, API, and compatibility changes, see GitHub Releases.

The current docs site history starts at 0.2.2.

0.2.5

• Added Kimi Delta Attention (KDA) decode coverage to Python APIs and KDA.

• Expanded Attention for FMHA only_qv and MLA head-ratio coverage.

• Added MSA direct APIs and the MSA/fmha_sm100 wrapper for MiniMax Sparse Attention (MSA) workflows on MUSA.

• Updated Installing MATE for the MUSA simple package index.

• Added MUBIN artifact management commands to Command Line Interface.

• Refined FlashMLA/DenseMLA support for multiple head-ratio configurations.

0.2.4

• Updated Installing MATE for wrapper-first pip installation, including automatic mate dependency installation.

• Added W4A8 mixed-dtype MoE GEMM to Python APIs and GEMM.

• Added Mega MoE to Python APIs and Mega MoE.

0.2.3

• Expanded the docs set around Overview, Installing MATE, Wrappers, Diagnostic Overview, Command Line Interface, Design and Architecture, and Python APIs.

• Added wrapper pages for FlashAttention, SageAttention, FlashMLA, FlashKDA, and DeepGEMM.

• Added API pages for Attention, GEMM, HyperConnection, and KDA.

• Moved Command Line Interface, Environment Variables, and GDN Support Matrix into the Sphinx site structure.

0.2.2

• Established the initial public docs baseline in the home page and the early API set.

• Added the HyperConnection API page.

• Updated FlashAttention and GDN Support Matrix.

• Refreshed the home page structure.