llama-cpp-capacitor

Version:

A native Capacitor plugin that embeds llama.cpp directly into mobile apps, enabling offline AI inference with chat-first API design. Complete iOS and Android support: text generation, chat, multimodal, TTS, LoRA, embeddings, and more.

github.com/arusatech/llama-cpp

arusatech/llama-cpp

2 folders, 20 files

Filename	Content Type	Size
../
amx/	–	118 kB
arch/	–	1.11 MB
arch-fallback.h	application/octet-stream	13.9 kB
binary-ops.cpp	application/octet-stream	7.05 kB
binary-ops.h	application/octet-stream	554 B
common.h	application/octet-stream	1.9 kB
ggml-cpu-impl.h	application/octet-stream	14.5 kB
ggml-cpu.c	application/octet-stream	122 kB
ggml-cpu.cpp	application/octet-stream	23.8 kB
ops.cpp	application/octet-stream	369 kB
ops.h	application/octet-stream	9.7 kB
quants.c	application/octet-stream	41 kB
quants.h	application/octet-stream	10.2 kB
repack.cpp	application/octet-stream	79.9 kB
repack.h	application/octet-stream	8.31 kB
simd-mappings.h	application/octet-stream	50.4 kB
traits.cpp	application/octet-stream	1.25 kB
traits.h	application/octet-stream	1.2 kB
unary-ops.cpp	application/octet-stream	6.03 kB
unary-ops.h	application/octet-stream	1.87 kB
vec.cpp	application/octet-stream	13.3 kB
vec.h	application/octet-stream	46.8 kB