master-f7f05fb

chore: avoid setting GGML_MAX_NAME when building against external ggm…

master-6167e29

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

master-5b8996f

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>

master-f6b9aa1

refector: optimize the usage of tensor_types

master-7eb30d0

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>

master-59080d3

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

master-eed97a5

sync: update ggml

master-bd1eaef

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

master-ab835f7

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

master-1896b28

fix: make --taesd work (#731)