add support for flux2 klein (#1193)

* add support for flux2 klein 4b

* add support for flux2 klein 8b

* use attention_mask in Flux.2 klein LLMEmbedder

* update docs

refactor: move pmid condition logic into get_pmid_condition (#1148)

refactor: split SDParams to SDCliParams/SDContextParams/SDGenerationP…

refactor: optimize the handling of sample method (#999)

fix: resolve issue with concat multiple LoRA output diffs at runtime …

feat: add cpu rng (#977)

refactor: simplify the model loading logic (#933)

* remove String2GGMLType

* remove preprocess_tensor

* fix clip init

* simplify the logic for reading weights

refactor: introduce GGMLRunnerContext (#928)

* introduce GGMLRunnerContext

* add Flash Attention enable control through GGMLRunnerContext

* add conv2d_direct enable control through GGMLRunnerContext

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

feat: add chroma radiance support (#910)

* add chroma radiance support

* fix ci

* simply generate_init_latent

* workaround: avoid ggml cuda error

* format code

* add chroma radiance doc