Update README.md

README.md

@@ -22,8 +22,17 @@ pip install sdnq
 import torch
 import diffusers
 from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers
+from sdnq.common import use_torch_compile as triton_is_available
+from sdnq.loader import apply_sdnq_options_to_model
 
 pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-dev-SDNQ-uint4-svd-r32", 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.text_encoder_2 = apply_sdnq_options_to_model(pipe.text_encoder_2, use_quantized_matmul=True)
+    pipe.transformer = torch.compile(pipe.transformer) # optional for faster speeds
+
 pipe.enable_model_cpu_offload()
 
 prompt = "A cat holding a sign that says hello world"