v2.0.0

[HolyWu]

• Add support for FP16 inference.
• Add num_streams, nvfuser, cuda_graphs and model parameters.
• Remove task, scale and device_type parameters.
• Add 2x_Bubble_AnimeScale_SwinIR_Small_v1 model from https://github.com/Bubblemint864/AI-Models.
• Remove classicalSR and realSR_BSRGAN_DFO_s64w8_SwinIR-M_x4_GAN models.

---

This discussion was created from the release v2.0.0.