efficient-transformers

Release Documents

  • Efficient Transformer Library - 1.21.0 Release Notes
  • Efficient Transformer Library - 1.20.0 Release Notes

Getting Started

  • Introduction Qualcomm efficient-transformers library
  • Supported Features
  • Validated Models
  • Models Coming Soon

Installation

  • Pre-requisites
  • Installation
  • Sanity Check

Inference on Cloud AI 100

  • Quick Start
  • Fetaures Enablement Guide

API Reference

  • QEfficient Auto Classes
  • Diffuser Classes
  • CLI API Reference

QAIC Finetune

  • Finetune Infra
  • Expose QAIC accelerator devices
  • Start Docker container

Blogs

  • Train anywhere, Infer on Qualcomm Cloud AI 100
  • How to Quadruple LLM Decoding Performance with Speculative Decoding (SpD) and Microscaling (MX) Formats on Qualcomm® Cloud AI 100
  • Power-efficient acceleration for large language models – Qualcomm Cloud AI SDK
  • Qualcomm Cloud AI 100 Accelerates Large Language Model Inference by ~2x Using Microscaling (Mx) Formats
  • Qualcomm Cloud AI Introduces Efficient Transformers: One API, Infinite Possibilities

Reference

  • Qualcomm Cloud AI home
  • Qualcomm Cloud AI SDK download
  • Qualcomm Cloud AI API reference
  • User Guide
  • OCP Microscaling Formats (MX) Specification
efficient-transformers
  • Overview: module code

All modules for which code is available

  • QEfficient.cloud.execute
  • QEfficient.cloud.export
  • QEfficient.cloud.finetune
  • QEfficient.cloud.infer
  • QEfficient.compile.compile_helper
  • QEfficient.diffusers.pipelines.flux.pipeline_flux
  • QEfficient.diffusers.pipelines.pipeline_module
  • QEfficient.diffusers.pipelines.wan.pipeline_wan
  • QEfficient.peft.auto
  • QEfficient.peft.lora.auto
  • QEfficient.transformers.models.modeling_auto

© Copyright 2025, Qualcomm.

Built with Sphinx using a theme provided by Read the Docs.
Version: Main
Versions
main
release/v1.18