chore: avoid setting GGML_MAX_NAME when building against external ggml (

#751)

An external ggml will most likely have been built with the default
GGML_MAX_NAME value (64), which would be inconsistent with the value
set by our build (128). That would be an ODR violation, and it could
easily cause memory corruption issues due to the different
sizeof(struct ggml_tensor) values.

For now, when linking against an external ggml, we demand it has been
patched with a bigger GGML_MAX_NAME, since we can't check against a
value defined only at build time.

feat: support build against system installed GGML library (#749)

Conv2D direct support (#744)

* Conv2DDirect for VAE stage

* Enable only for Vulkan, reduced duplicated code

* Cmake option to use conv2d direct

* conv2d direct always on for opencl

* conv direct as a flag

* fix merge typo

* Align conv2d behavior to flash attention's

* fix readme

* add conv2d direct for controlnet

* add conv2d direct for esrgan

* clean code, use enable_conv2d_direct/get_all_blocks

* format code

---------

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

refector: optimize the usage of tensor_types

feat: change image dimensions requirement for DiT models (#742)

feat: add missing models and parameters to image metadata (#743)

* feat: add new scheduler types, clip skip and vae to image embedded params

- If a non default scheduler is set, include it in the 'Sampler' tag in the data
embedded into the final image.
- If a custom VAE path is set, include the vae name (without path and extension)
in embedded image params under a `VAE:` tag.
- If a custom Clip skip is set, include that Clip skip value in embedded image
params under a `Clip skip:` tag.

* feat: add separate diffusion and text models to metadata

---------

Co-authored-by: one-lithe-rune <skapusniak@lithe-runes.com>

sync: update ggml

fix: convert f64 to f32 and i64 to i32 when loading weights

fix: correct head dim check and L_k padding of flash attention (#736)

fix: make --taesd work (#731)