Deploying VITA-1.5 Multimodal Model with ExecuTorch
Open
Nobody has claimed this yet.
module: llm
triaged
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
🚀 The feature, motivation and pitch
I’m trying to deploy a VITA-1.5 multimodal model (supports audio, vision, and text) using ExecuTorch.
The tokenizer is in Hugging Face tokenizer.json format, and I’d like to ask:
- Is there any suggested way to convert the model into .pte format for ExecuTorch?
- Since this is a new architecture, is there any guidance or examples for adding custom models?
- Can I still use the LlamaDemo Android app with this multimodal？
Alternatives
No response
Additional context
No response
RFC (Optional)
No response
cc @larryliu0820 @mergennachin @cccclai @helunwencser @jackzhxng
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no repository files, tests, or entry points. Begin by locating existing ExecuTorch model-conversion guidance, custom-model examples, and the LlamaDemo Android app to compare their supported workflows. Done would require resolving the .pte conversion, custom-architecture guidance, and multimodal Android compatibility questions.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- android, python, pytorch
- Domain
- machine-learning, mobile-dev
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100