sd: sync with master-719-f440ad9

[wbruna]

master-714-b12098f:

• Boogu-Image support
• fixes for Anima and Ernie with Vulkan + Flash Attention
• a CLIP normalization fix
• dropped the assertion failure for SD_TYPE_COUNT != GGML_TYPE_COUNT, which shouldn't be needed anymore
• enabled the mmproj for LongCat-Image Edit (although I haven't had much luck with it)

[wbruna]

I'm hitting an assertion failure with Boogu-Image Edit:

ggml/src/ggml.c:2612: GGML_ASSERT(a->ne[d] == b->ne[d]) failed

so I've disabled its edit mode for now.

Edit: I can't reproduce the crash with stable-diffusion.cpp.

[wbruna]

Oddly, after removing the mmproj (I guess Qwen3-VL has it built-in), and reducing cfg to 1, I've got the edit mode working:

[LostRuins]

does it need any tensor loading hacks?

[wbruna]

Apart from the llm and mmproj redirects, I didn't need any. But I didn't try a downloaded quant; for the images above I've used q8_0 quants I've converted myself (with a simple --type q8_0). Working both on Vulkan and ROCm.

[wbruna]

master-719-f440ad9:

• mmap fix
• guidance_schedule parameter (useful for Ideogram once supported)
• eager_load parameter to preload weights (but doesn't seem to work without streaming)