547765a93e
* mtmd: add Gemma 4 audio conformer encoder support Add audio processing for Gemma 4 E2B/E4B via a USM-style Conformer. Architecture: - 12-layer Conformer: FFN → Self-Attention → Causal Conv1D → FFN → Norm - Subsampling Conv Projection: 2x Conv2D(stride=2) with LayerNorm - Full self-attention with sinusoidal RPE and sliding window mask (24) - Logit softcapping at 50.0, ClippableLinear clamping - Output: 1024 → 1536 → RMSNorm → multimodal embedder Mel preprocessing (dedicated mtmd_audio_preprocessor_gemma4a): - HTK mel scale, 128 bins, magnitude STFT, mel_floor=1e-3 - Standard periodic Hann window (320 samples), zero-padded to FFT size - Semicausal left-padding (frame_length/2 samples) - Frame count matched to PyTorch (unfold formula) - No pre-emphasis, no Whisper-style normalization - Mel cosine similarity vs PyTorch: 0.9998 Key fixes: - Tensor loading dedup: prevent get_tensor() from creating duplicate entries in ctx_data. Fixed with std::set guard. - ClippableLinear clamp_info loading moved after per-layer tensors. - Sliding window mask (24 positions) matching PyTorch context_size. - Skip Whisper normalization for Gemma4 mel output. Tested on E2B and E4B with CPU and Vulkan backends. Transcribes: "Glad to see things are going well and business is starting to pick up" (matching ground truth). Ref: #21325 |
||
|---|---|---|
| .. | ||
| debug | ||
| legacy-models | ||
| models | ||
| tests | ||
| CMakeLists.txt | ||
| README.md | ||
| clip-graph.h | ||
| clip-impl.h | ||
| clip-model.h | ||
| clip.cpp | ||
| clip.h | ||
| deprecation-warning.cpp | ||
| mtmd-audio.cpp | ||
| mtmd-audio.h | ||
| mtmd-cli.cpp | ||
| mtmd-helper.cpp | ||
| mtmd-helper.h | ||
| mtmd-image.cpp | ||
| mtmd-image.h | ||
| mtmd.cpp | ||
| mtmd.h | ||
| requirements.txt | ||
| test-1.jpeg | ||
| test-2.mp3 | ||
| tests.sh | ||
README.md
Multimodal Support in llama.cpp
This directory provides multimodal capabilities for llama.cpp. Initially intended as a showcase for running LLaVA models, its scope has expanded significantly over time to include various other vision-capable models. As a result, LLaVA is no longer the only multimodal architecture supported.
[!IMPORTANT]
Multimodal support can be viewed as a sub-project within
llama.cpp. It is under very heavy development, and breaking changes are expected.
The naming and structure related to multimodal support have evolved, which might cause some confusion. Here's a brief timeline to clarify:
- #3436: Initial support for LLaVA 1.5 was added, introducing
llava.cppandclip.cpp. Thellava-clibinary was created for model interaction. - #4954: Support for MobileVLM was added, becoming the second vision model supported. This built upon the existing
llava.cpp,clip.cpp, andllava-cliinfrastructure. - Expansion & Fragmentation: Many new models were subsequently added (e.g., #7599, #10361, #12344, and others). However,
llava-clilacked support for the increasingly complex chat templates required by these models. This led to the creation of model-specific binaries likeqwen2vl-cli,minicpmv-cli, andgemma3-cli. While functional, this proliferation of command-line tools became confusing for users. - #12849:
libmtmdwas introduced as a replacement forllava.cpp. Its goals include providing a single, unified command-line interface, improving the user/developer experience (UX/DX), and supporting both audio and image inputs. - #13012:
mtmd-cliwas added, consolidating the various model-specific CLIs into a single tool powered bylibmtmd.
Pre-quantized models
See the list of pre-quantized model here
How it works and what is mmproj?
Multimodal support in llama.cpp works by encoding images into embeddings using a separate model component, and then feeding these embeddings into the language model.
This approach keeps the multimodal components distinct from the core libllama library. Separating these allows for faster, independent development cycles. While many modern vision models are based on Vision Transformers (ViTs), their specific pre-processing and projection steps can vary significantly. Integrating this diverse complexity directly into libllama is currently challenging.
Consequently, running a multimodal model typically requires two GGUF files:
- The standard language model file.
- A corresponding multimodal projector (
mmproj) file, which handles the image encoding and projection.
What is libmtmd?
As outlined in the history, libmtmd is the modern library designed to replace the original llava.cpp implementation for handling multimodal inputs.
Built upon clip.cpp (similar to llava.cpp), libmtmd offers several advantages:
- Unified Interface: Aims to consolidate interaction for various multimodal models.
- Improved UX/DX: Features a more intuitive API, inspired by the
Processorclass in the Hugging Facetransformerslibrary. - Flexibility: Designed to support multiple input types (text, audio, images) while respecting the wide variety of chat templates used by different models.
How to obtain mmproj
Multimodal projector (mmproj) files are specific to each model architecture.
For the following models, you can use convert_hf_to_gguf.py with --mmproj flag to get the mmproj file:
- Gemma 3 ; See the guide here - Note: 1B variant does not have vision support
- SmolVLM (from HuggingFaceTB)
- SmolVLM2 (from HuggingFaceTB)
- Pixtral 12B - only works with
transformers-compatible checkpoint - Qwen 2 VL and Qwen 2.5 VL (from Qwen)
- Mistral Small 3.1 24B
- InternVL 2.5 and InternVL 3 from OpenGVLab (note: we don't support conversion of
InternVL3-*-hfmodel, only non-HF version is supported ;InternLM2Modeltext model is not supported)
For older models, please refer to the relevant guide for instructions on how to obtain or create them:
NOTE: conversion scripts are located under tools/mtmd/legacy-models