v0.7.0

github-actions released this 18 Mar 23:43

· 38 commits to main since this release

dc526da

v0.7.0 (2026-03-18)

This release is published under the Apache-2.0 License.

Features

Add Multi-Latent Attention implementation along with support for different RoPE layouts (56684bc)
Add Qwen3 Dense model (08047bd)

Detailed Changes: v0.6.0...v0.7.0

Assets 4