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 package

quantization

This package contains a set of APIs for quantizing tensor data.

Quantization is a technique used to reduce the precision of floating-point numbers, which are used in most neural networks. Quantization is a type of lossy compression, which means that some precision is lost, but the resulting tensors take less memory and computations are faster.

Modules

• ​per_channel_grouped_4bit: Provides per-channel grouped 4-bit quantization and K-quant dequantization kernels.
• ​qmatmul: Provides CPU kernels for block-wise quantized int4 matrix multiplication.
• ​qmatmul_gpu: Provides GPU kernels for block-wise quantized int4 matrix multiplication.
• ​qmatmul_k: Provides CPU kernels for K-quant block-wise quantized matrix multiplication.

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