Instructions to use flashrt/fp4-fused-ops with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use flashrt/fp4-fused-ops with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("flashrt/fp4-fused-ops") - Transformers
How to use flashrt/fp4-fused-ops with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("flashrt/fp4-fused-ops", device_map="auto") - Diffusers
How to use flashrt/fp4-fused-ops with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("flashrt/fp4-fused-ops", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle