fix: detect model format base on file content

feat: load weights from safetensors and ckpt (leejet#101)

fix: allow model and vae using different format

fix: avoid build fail on msvc (leejet#93)

fix: reading memory of stack allocated object past its scope (leejet#91)

feat: ggml-alloc integration and gpu acceleration (leejet#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>

feat: allow LoRAs with negative multiplier (leejet#83)

* Allow Loras with negative weight, too.

There are a couple of loras, which serve to adjust certain concepts in
both positive and negative directions (like exposure, detail level etc).

The current code rejects them if loaded with a negative weight, but I
suggest that this check can simply be dropped.

* ignore lora in the case of multiplier == 0.f

---------

Co-authored-by: Urs Ganse <urs@nerd2nerd.org>
Co-authored-by: leejet <leejet714@gmail.com>

chore: add .clang-format

chore: typo remote => remove

feat: add LoRA support