Does your weight format deserve a kernel?
Pack model weights, unpack them to bf16, and test quality in stock MLX before building support for a new format.
Read article : Does your weight format deserve a kernel?What we learn along the way
Notes on engineering, research and building a company.
The rounding quirk hiding inside RMSNorm
In the RMSNorm paths we examined, MLX rounds earlier than PyTorch, NVIDIA Transformer Engine and Huawei CANN. That small choice matters when moving models between platforms.
Read article : The rounding quirk hiding inside RMSNormWhy we started writing
Some useful things disappear between the first question and the finished result. After twelve years, we have made a place to keep them.
Read article : Why we started writingThere are no articles in this category yet.
What are you curious about?
We enjoy turning interesting questions into useful things.
Let’s talk about yours.