Add Ideogram support and improve BF16 dequantization handling

[molbal]

Summary

This adds support for Ideogram GGUF models.

What Changed

• Added ideogram to the supported image GGUF architectures.
• Added Ideogram model detection to the converter.
• Added GGUF dtype handling needed by Ideogram inference.
• Fixed the Ideogram inference failure where a packed GGUF weight dtype caused a byte tensor to reach CUDA linear.
• Adjusted BF16 GGUF loading so Ideogram can start inference faster.

Notes

Tested on Windows 11, Python version: 3.12.11 (main, Jul 23 2025, 00:32:20) [MSC v.1944 64 bit (AMD64)] [INFO] Total VRAM 8192 MB, total RAM 48394 MB
[INFO] pytorch version: 2.12.0+cu130
[INFO] Set vram state to: LOW_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 3080 Laptop GPU

Tested with Q4_0 gguf from https://huggingface.co/leejet/ideogram-4-GGUF

Other GGUF quant types still use the existing dequant paths.

[yu234567]

Great! I successfully ran it, but my device doesn't support bf16; it gets converted to fp32 computation, which makes it very slow. Can you make it run on my device in fp16?

---

[INFO] got prompt
[INFO] Using xformers attention in VAE
[INFO] Using xformers attention in VAE
[INFO] VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
[INFO] Found quantization metadata version 1
[INFO] Using MixedPrecisionOps for text encoder
[INFO] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Requested to load Ideogram4TEModel_
[INFO] Model Ideogram4TEModel_ prepared for dynamic VRAM loading. 4319MB Staged. 0 patches attached. Force pre-loaded 144 weights: 594 KB.
[WARNING] Warning: This gguf model file is loaded in compatibility mode 'sd.cpp' [arch:ideogram]
[INFO] gguf qtypes: BF16 (254), Q4_0 (204)
[INFO] model weight dtype torch.bfloat16, manual cast: torch.float32
[INFO] model_type FLOW
[INFO] Requested to load Ideogram4
[INFO] loaded completely; 7997.15 MB usable, 5506.41 MB loaded, full load: True
8%|████ | 1/12 [00:16<03:03, 16.65s/it, Model Initialization complete! ][INFO] Interrupting prompt 2d4b1e4f-b3b1-4a31-9d36-604af4910de5

[molbal]

Hi @yu234567 - try now. It should work better now, can you verify please?

[yu234567]

Hi @yu234567 - try now. It should work better now, can you verify please?

Thank you so much, it worked!

[Pranjwal-Jha]

classifies Qwen3-VL-8B-Instruct q4_0 quant as _k quant and errors out ? is this expected or what quantization are you running for the te