Anandharaju Durai Raju

icon indicating a website link anandharaju.github.io icon indicating an email [email protected]

icon location Vancouver, BC, Canada icon location Grad @SimonFraserUniversity - Deep Learning, Data Mining, Cybersecurity, Malware detection, Lateral movement detection, Python, Java

Results 1 issues of Anandharaju Durai Raju

H100 GPU - FP8 inference acceleration

1 comment

Thanks for the great work ! I followed the Qwen-Image inference example in below link (recommended for faster inference) for comparing FP8 vs bfloat16: [./accelerate/Qwen-Image-FP8.py](https://github.com/modelscope/DiffSynth-Studio/blob/833ba1e1fa5d36826d5b21d6628baa17ac1e6f4d/examples/qwen_image/accelerate/Qwen-Image-FP8.py) But for FP8 (torch.float8_e4m3fn), the...