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

* remove String2GGMLType

* remove preprocess_tensor

* fix clip init

* simplify the logic for reading weights

fix: optimize the handling of embedding weight (leejet#859)

refactor: remove unused --normalize-input parameter (leejet#835)

chore: set release tag by commit count

feat: add sd3 flash attn support (leejet#815)

feat: add wan2.1/2.2 support (leejet#778)

* add wan vae suppport

* add wan model support

* add umt5 support

* add wan2.1 t2i support

* make flash attn work with wan

* make wan a little faster

* add wan2.1 t2v support

* add wan gguf support

* add offload params to cpu support

* add wan2.1 i2v support

* crop image before resize

* set default fps to 16

* add diff lora support

* fix wan2.1 i2v

* introduce sd_sample_params_t

* add wan2.2 t2v support

* add wan2.2 14B i2v support

* add wan2.2 ti2v support

* add high noise lora support

* sync: update ggml submodule url

* avoid build failure on linux

* avoid build failure

* update ggml

* update ggml

* fix sd_version_is_wan

* update ggml, fix cpu im2col_3d

* fix ggml_nn_attention_ext mask

* add cache support to ggml runner

* fix the issue of illegal memory access

* unify image loading processing

* add wan2.1/2.2 FLF2V support

* fix end_image mask

* update to latest ggml

* add GGUFReader

* update docs

sync: update ggml, make cuda im2col a little faster

refector: optimize the usage of tensor_types

fix: ModelLoader::load_tensors duplicated check (leejet#623)

Introduced in 2b6ec97

chore: silence some warnings about precision loss (leejet#620)