jinweida

does NVIDIA L20 GPUs support FP8 quantization?

9

### System Info CPU architecture: x86_64 Host RAM: 1TB GPU: 2xL20 SXM Container: Manually built container with TRT 9.3 Dockerfile.trt_llm_backend TensorRT-LLM version: 0.12.0.dev2024070200" Driver Version: 550.54.15 CUDA Version: 12.4 OS:...

code `from melo.api import TTS import os import glob import sys import nltk # 设置NLTK数据存储路径（可替换为自定义路径，如当前用户目录下的nltk_data） nltk_data_path = os.path.expanduser("/data/ai/hub/nltk_data") os.environ["NLTK_DATA"] = nltk_data_path model_dir="/data/ai/hub/myshell-ai/MeloTTS-Chinese" language = sys.argv[1] print(f"language: {language}") checkpoint=os.path.join(model_dir, "checkpoint.pth") print(f"model_dir...