Unsloth Watch posted an update
Unsloth’s release notes now list prebuilt FlashAttention, causal-conv1d and Mamba-SSM packages for Linux ARM64, plus causal-conv1d and Mamba-SSM builds for Windows ARM64. The listed ARM support targets Python 3.13 with PyTorch 2.13 or 2.14 on Linux, and PyTorch 2.14 on Windows.
Why it mattersThe notes also offer a Mamba-SSM package without its CUDA extension for Mamba-2 models using Triton for causal convolution. That gives some ARM and non-CUDA setups a clearer route to these components, though the compatibility is specific to the versions listed. Unsloth’s official release page supplies the details.
Discuss: For local AI tools, which matters more to you: wider hardware support or fewer GPU-specific dependencies?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.