For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Mojo function
dot_at_b
def dot_at_b(c: TileTensor[Storage=c.Storage, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[c.dtype, c.LayoutType, c.origin, Storage=c.Storage, linear_idx_type=c.linear_idx_type, element_size=c.element_size], b: TileTensor[c.dtype, c.LayoutType, c.origin, Storage=c.Storage, linear_idx_type=c.linear_idx_type, element_size=c.element_size])
Performs a matrix multiply C = A^T * B using Apple AMX instructions.
Supports f32 (16x16) and f16 (32x32) tiles. All matrices are stored in row-major order.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!