Disty0
/

Ideogram-4-SDNQ-4bit-dynamic-hadamard

Ideogram4Pipeline

4-bit precision

8-bit precision

Model card Files Files and versions

Disty0 commited on Jun 10

Commit

270feac

·

verified ·

1 Parent(s): babec99

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -38,7 +38,7 @@ from sdnq.loader import apply_sdnq_options_to_model
 pipe = diffusers.Ideogram4Pipeline.from_pretrained("Disty0/Ideogram-4-SDNQ-4bit-dynamic-hadamard", torch_dtype=torch.bfloat16)
-# Enable INT8 MatMul for AMD, Intel ARC and Nvidia GPUs:
 if triton_is_available and (torch.cuda.is_available() or torch.xpu.is_available()):
     pipe.transformer = apply_sdnq_options_to_model(pipe.transformer, use_quantized_matmul=True)
     pipe.unconditional_transformer = apply_sdnq_options_to_model(pipe.unconditional_transformer, use_quantized_matmul=True)

 pipe = diffusers.Ideogram4Pipeline.from_pretrained("Disty0/Ideogram-4-SDNQ-4bit-dynamic-hadamard", torch_dtype=torch.bfloat16)
+# Enable INT8 and FP8 MatMul for AMD, Intel ARC and Nvidia GPUs:
 if triton_is_available and (torch.cuda.is_available() or torch.xpu.is_available()):
     pipe.transformer = apply_sdnq_options_to_model(pipe.transformer, use_quantized_matmul=True)
     pipe.unconditional_transformer = apply_sdnq_options_to_model(pipe.unconditional_transformer, use_quantized_matmul=True)