master-8124588

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 <[email protected]>

master-ae1d5dc

feat: allow LoRAs with negative multiplier (#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 <[email protected]>
Co-authored-by: leejet <[email protected]>

master-9a9f3da

feat: add LoRA support

master-51b53d4

chore: typo remote => remove

master-176a00b

chore: add .clang-format

master-0d9b801

fix: fix multi loras prompt parse

master-536f3af

feat: add lcm sampler support

This referenced an issue discussion of the stable-diffusion-webui at
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13952, which
may not be too perfect.

master-3bf1665

chore: clear the msvc compilation warning

master-ed37498

fix: set eps of ggml_norm(LayerNorm) to 1e-5

master-fbd18e1

fix: avoid stack overflow on MSVC