Skip to content

MLLM
2.0.0 documentation

MLLM
2.0.0 documentation

Quick Start

Mllm API Service
- MLLM CLI

Architectures

Compile
- MLLM IR

Quantization
- Data Types in MLLM
- How to Add New Data Types

MLLM LM Cache

CPU Backend

Ascend Backend
- Ascend Backend

QNN Backend

OpenCL Backend

MLLM C++ API

Contribute

Talks

Algorithm
- Pruning

FAQ

Pymllm API

pymllm

pymllm.mobile.quantize.gguf¶

pymllm.mobile.quantize.kai

pymllm.mobile.quantize.cast2fp32_pass

Copyright © 2024-2025, MLLM Contributors

Made with Sphinx and @pradyunsg's Furo