Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

feat(local-apps): Add Nexa SDK integration#1800

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Open
mengshengwu wants to merge2 commits intohuggingface:main
base:main
Choose a base branch
Loading
frommengshengwu:feat/nexa-sdk

Conversation

@mengshengwu
Copy link

@mengshengwumengshengwu commentedOct 14, 2025
edited
Loading

Introduction

Hello! Friends from Huggingface 👋

Thank you for maintaining this amazing library and ecosystem.
Following a recent discussion with Hugging Face (seehere), your CEO expressed interest in exploring collaboration to bringon-device model inference to the community. This PR proposes addingNexa SDK to the local apps section as a new runtime integration option.

About Nexa SDK

Nexa SDK is an on-device inference framework that runs any model on any device, across any backend. It runs on CPUs, GPUs, NPUs with backend support for CUDA, Metal, Vulkan, and Qualcomm / Intel / AMD NPU. It handles multiple input modalities including text 📝, image 🖼️, and audio 🎧. The SDK includes an OpenAI-compatible API server with support for JSON schema-based function calling and streaming. It supports model formats such as GGUF, MLX, Nexa AI's own.nexa format, enabling efficient quantized inference across diverse platforms.


Example Demos

Multi-Image Reasoning Demo

🖼️ Multi-Image Reasoning
Spot the difference across two images in multi-round dialogue.

Image + Audio Function Call Demo

🎤 Image + Text → Function Call
Snap a poster, add a voice note, and the AI agent creates a calendar event locally.

Multi-Audio Comparison Demo

🎶 Multi-Audio Comparison
Identify differences between two music clips — fully offline.


Related Links


Logo File

Nexa-Logo-Black


Thank you for your time reviewing this PR!
We’re excited to explore how Nexa SDK can extend Hugging Face models to mobile and edge platforms. 🙏

@mengshengwumengshengwu changed the titlefeat(tasks): update Nexa SDK integration with multi-platform supportfeat(local-apps): Add Nexa SDK integrationOct 14, 2025
@zhiyuan8
Copy link

@SBrandeis@Wauplin@julien-c@pcuenca look forward to your review feedbacks!

Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment

Reviewers

@SBrandeisSBrandeisAwaiting requested review from SBrandeisSBrandeis is a code owner

@gary149gary149Awaiting requested review from gary149gary149 is a code owner

@WauplinWauplinAwaiting requested review from WauplinWauplin is a code owner

@julien-cjulien-cAwaiting requested review from julien-cjulien-c is a code owner

@pcuencapcuencaAwaiting requested review from pcuencapcuenca is a code owner

@ngxsonngxsonAwaiting requested review from ngxsonngxson is a code owner

1 more reviewer

@RemiliaForeverRemiliaForeverRemiliaForever left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@mengshengwu@zhiyuan8@RemiliaForever

[8]ページ先頭

©2009-2025 Movatter.jp