Feature Request: mmproj GPU processing while offloading weights

Abierto
#179 2 comentarios 0 reacciones 0 asignados Ver en GitHub

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
5/5
Tiempo estimado
Más de una semana
Aptitud para principiantes
20/100
Tipo de issue
Nueva funcionalidad
Claridad
Bastante claro
Estado de actividad
Tranquilo
Stack tecnológico
cpp

Línea de trabajo

Start from the README and the linked llama.cpp discussion #20246, then trace how the existing --mmproj-offload and --no-mmproj-offload options are wired through the CLI and multimodal projector loading. The issue names no source files, so the first task is to locate the mmproj load/encode path and the model-specific projector implementations such as Qwen and Gemma before proposing a design. Done means a documented, working third mode that keeps image encoding on GPU without permanent full projector residency.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

enhancement
Prerequisites
  • I am running the latest code. Mention the version if possible as well.
  • I carefully followed the README.md.
  • I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
  • I reviewed the Discussions, and have a new and useful enhancement to share.
Feature Description

I would like to request an option to use GPU-accelerated vision processing without keeping the complete multimodal projector permanently resident in VRAM.

Currently there are essentially two choices:

--mmproj-offload: fast GPU image encoding, but the projector permanently consumes a significant amount of VRAM.

--no-mmproj-offload: saves the VRAM, but image encoding runs on the CPU and can be considerably slower.

What I would like is a third option: keep the VRAM available for the LLM / KV cache most of the time, while still performing image encoding on the GPU.

There already seem to be several approaches demonstrating that this is possible:

https://github.com/ggml-org/llama.cpp/discussions/20246

https://github.com/Anbeeld/beellama.cpp/issues/140

https://github.com/valujin/beellama-kvarn

I also encountered a similar low-VRAM GPU vision approach while testing HyperQwen / vLLM.

Motivation

Currently, loading mmproj typically consumes around 1 GB of VRAM.

On VRAM-constrained GPUs, this is quite significant, especially when running large models with long context windows. That VRAM could otherwise be used for additional context, larger KV cache, draft models, or other features.

CPU-based image processing is an alternative, but in my experience it creates substantial overhead and is much slower.

For this reason, I currently often disable mmproj completely for Qwen and Gemma models: keeping it on the GPU costs too much VRAM, while processing images on the CPU is too expensive.

A low-memory GPU implementation would provide a useful middle ground:

  • fast GPU-based image processing

  • very low additional VRAM usage

  • more VRAM available for context and KV cache

  • no need to choose between fast vision processing and large context sizes

For users running modern multimodal models on GPUs with limited VRAM, this could make a substantial difference.

Possible Implementation

HyperQwen may provide a useful reference implementation. Its vLLM-based implementation seems to use a sliding-window approach for image processing, allowing the processing to remain GPU-accelerated while using only a very small amount of VRAM.

The related llama.cpp discussion also appears to cover approaches in this direction:

https://github.com/ggml-org/llama.cpp/discussions/20246

I assume that a fully model-independent implementation may not be straightforward, since projector architectures differ between model families.

Still, even an implementation initially targeting a few common architectures such as Qwen and Gemma could already be very useful, and might provide a basis for a more generic solution later.

Lenguaje dominante
C++
Estrellas
1.2k
Forks
80
Merge medio
4 d 20 h
PR fusionados (30 d)
2

Preparar el entorno

Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de Anbeeld/beellama.cpp

Todos los issues de Anbeeld/beellama.cpp

Issues similares

Más issues de C++

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.