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 module

qmatmul

Provides CPU kernels for block-wise quantized int4 matrix multiplication.

comptime values

K_BATCH_SIZE

comptime K_BATCH_SIZE = 512

Defines the batch size of K used to pack A and unpack B weights.

Functions

• ​matmul_qint4: Computes a matrix multiply of a float32 A matrix against block-wise quantized int4 B weights, producing a float32 result.
• ​matmul_qint4_pack_b: Repacks block-wise quantized int4 weights into the tiled layout expected by the matmul_qint4 kernels.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit