Principle:Ggml org Llama cpp Multimodal
| Knowledge Sources | Domains | Last Updated |
|---|---|---|
| ggml-org/llama.cpp | Vision Language Models, CLIP, Audio | 2026-02-15 |
Overview
Description
Multimodal is a design principle in the llama.cpp project covering vision language models, CLIP, and audio processing.
Usage
See linked implementation pages for concrete usage details.
Related Pages
- Implementation:Ggml_org_Llama_cpp_CLIP_Graph
- Implementation:Ggml_org_Llama_cpp_CLIP_Header
- Implementation:Ggml_org_Llama_cpp_CLIP_Impl
- Implementation:Ggml_org_Llama_cpp_CLIP_Model
- Implementation:Ggml_org_Llama_cpp_Mtmd_Audio
- Implementation:Ggml_org_Llama_cpp_Mtmd_Audio_Header
- Implementation:Ggml_org_Llama_cpp_Mtmd_Header
- Implementation:Ggml_org_Llama_cpp_Mtmd_Helper
- Implementation:Ggml_org_Llama_cpp_Mtmd_Helper_Header
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment