refactor: simplify the model loading logic (leejet#933)

* remove String2GGMLType

* remove preprocess_tensor

* fix clip init

* simplify the logic for reading weights

refactor: introduce GGMLRunnerContext (leejet#928)

* introduce GGMLRunnerContext

* add Flash Attention enable control through GGMLRunnerContext

* add conv2d_direct enable control through GGMLRunnerContext

fix: resolve multiple inpainting issues (leejet#926)

* Fix inpainting masked image being broken by side effect

* Fix unet inpainting concat not being set

* Fix Flex.2 inpaint mode crash (+ use scale factor)

refactor: unify the naming style of ggml extension functions (leejet#921

)

chore: clean up stb includes (leejet#919)

feat: add chroma radiance support (leejet#910)

* add chroma radiance support

* fix ci

* simply generate_init_latent

* workaround: avoid ggml cuda error

* format code

* add chroma radiance doc

feat: add SSD1B and tiny-sd support (leejet#897)

* feat: add code and doc for running SSD1B models

* Added some more lines to support SD1.x with TINY U-Nets too.

* support SSD-1B.safetensors

* fix sdv1.5 diffusers format loader

---------

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

feat: allow models to run without all text encoder(s) (leejet#645)

fix: support `--flow-shift` for flux models with default pred (leejet…

…#913)

feat: add shift factor support (leejet#903)