Weimin Wu
Weimin Wu
Hi, thanks for your reply! The answers are as the following: 1. try.py: import torch from rinalmo.pretrained import get_pretrained_model DEVICE = "cuda" model, alphabet = get_pretrained_model(model_name="giga-v1") model = model.to(device=DEVICE) seqs...
The error when installing 2.3.2: /home/vqc8153/miniconda3/envs/rna/lib/python3.11/site-packages/torch/include/c10/util/string_view.h:10:23: fatal error: string_view: No such file or directory #include ^ compilation terminated. fatal : Could not open input file /tmp/tmpxft_00034b5a_00000000-8_flash_fwd_split_hdim224_fp16_sm80.compute_80.cpp1.ii [49/49] /home/vqc8153/miniconda3/envs/rna/bin/nvcc --generate-dependencies-with-compile --dependency-output...
Thanks for your reply, my pytorch version is : 2.2.2+cu121 My g++ version is : g++ (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44) My gcc version is : gcc (GCC) 4.8.5...
Yes, I have tried "fresh" Conda environment
Thanks very much, I will try it!
No, I didn't. It maybe the model donot support the newest version of Falsh-attn. I want to ask for help from thr author as well