feat: ggml-alloc integration and gpu acceleration (#75)

* set ggml url to FSSRepo/ggml

* ggml-alloc integration

* offload all functions to gpu

* gguf format + native converter

* merge custom vae to a model

* full offload to gpu

* improve pretty progress

---------

Co-authored-by: leejet <leejet714@gmail.com>

examples/convert/CMakeLists.txt

@@ -0,0 +1,5 @@
+set(TARGET convert)
+
+add_executable(${TARGET} convert.cpp vocab.hpp)
+target_link_libraries(${TARGET} PRIVATE ggml zip ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PUBLIC cxx_std_11)

examples/convert/README.md

@@ -0,0 +1,16 @@
+# Model Convert
+
+## Usage
+```
+usage: convert.exe [MODEL_PATH] --type [OUT_TYPE] [arguments]
+Model supported for conversion: .safetensors models or .ckpt checkpoints models
+
+arguments:
+  -h, --help                         show this help message and exit
+  -o, --out [FILENAME]               path or name to converted model
+  --vocab [FILENAME]                 path to custom vocab.json (usually unnecessary)
+  -v, --verbose                      print processing info - dev info
+  -l, --lora                         force read the model as a LoRA
+  --vae [FILENAME]                   merge a custom VAE
+  -t, --type [OUT_TYPE]              output format (f32, f16, q4_0, q4_1, q5_0, q5_1, q8_0)
+```