FastFold

FastFold copied to clipboard

In current environment.yml conda not install cuda related package, that lead pytorch choose cpu version instead cuda version. and will fail when python setup.py install or run the infer.py

ycsos

how to use .a3m file as input

1

Hi, Can i use fastfold to run just inference? for example, I dont need jackmmer to run the msa search, I already have my msa search result (.a3m file) ready....

lzhangUT

Inference speed

1

Hi, I try to run inference scripts using T1050.fasta(779 residues) on nvidia a100, the following table shows the in time. Type | Inference time -- | -- FastFold | 262.14789s...

llwx593

The error of "Some NCCL operations have failed or timed out. Due to the asynchronous nature of CUDA kernels....."

2

Hello, How can i fix this error? When I ran the command, and the command is ok in my view: torchrun --nproc_per_node=4 inference.py ../testFasta/PsCrtW-HpCrtZ.fasta ../databases/pdb_mmcif/mmcif_files/ --output_dir ./output_4gpu --uniref90_database_path ../databases/uniref90/uniref90.fasta --mgnify_database_path...

heavenAsk

Warning: Torch did not find available GPUs on this system.

2

Hi, When I installed fastfold, I meet the following problem.  I think it's because I don't have a cuda environment on the cluster server (cpu node, non-root user) (but...

JOJO-wc-rabbit

About error of inference question

24

Hi! I installed the conda environment according to the content in the READMD, and then wrote a script to infer the protein structure. The content of the script is as...

zhoujingyu13687306871

Conda environment - no CUDA

1

Thanks for making this available, just a few comments on #installation I've been trying to get the CONDA environment to work on my systems, If I use the default environment...

arneelof

different dap

12

hi, I try different dap_size, such as dap_size=2, dap_size=4, but with the increase of dap, the decrease of gpu memory is not obvious, have you tried this？

liuxm117

About Training Settings

6

Can you provide init training and finetune training settings? model config, data config, not just table1 in the paper. e.g. whether use struct model? whether enable template? whether use extra...

GuoxiaWang

No module named 'fastfold_softmax_cuda'

5

I followed the installation instruction on anaconda but receive an error on `fastfold_softmax_cuda`. The machine has cuda version 11.6.2 installed. ``` Colossalai should be built with cuda extension to use...

SimonKitSangChu