Question:warning messages

[jd690764]

What is your question? I just installed localColabFold, so very new to this software. I ran the test case and the process finished all right with using the GPU. However, I get warning messages along the way:

(/home/pkj/localcolabfold/colabfold-conda) pkj@peacock:~$ colabfold_batch --amber --templates --num-recycle 3 /home/pkj/test/samples/O15552.fasta O15552_output_redo & [1] 11735 (/home/pkj/localcolabfold/colabfold-conda) pkj@peacock:~$ 2023-06-15 13:14:49,569 Running colabfold 1.5.2 (affc6e0e89ee723795ab009f51f2600d843dafb0) 2023-06-15 13:14:50.739387: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT 2023-06-15 13:14:51,099 Running on GPU 2023-06-15 13:14:51.112977: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1956] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2023-06-15 13:14:51,378 Found 8 citations for tools or databases 2023-06-15 13:14:51,378 Query 1/1: sp_O15552_FFAR2_HUMAN_Free_fatty_acid_receptor_2_OS_Homo_sapiens_OX_9606_GN_FFAR2_PE_1_SV_1 (length 330) COMPLETE: 100%| 150/150 [elapsed: 00:01 remaining: 00:00] 2023-06-15 13:15:00,843 Sequence 0 found templates: ['7f6g_A', '4n6h_A', '7wq3_R', '6pt2_B', '8ef5_M', '8efb_R', '7ul4_A', '6vi4_A', '7sbf_R', '8f7w_R', '7u2l_D', '6dde_R', '7yit_A', '7wic_R', '7t11_R', '7ul5_A', '7xat_A', '7t10_R', '7yae_E', '7wig_R'] 2023-06-15 13:15:01,056 Setting max_seq=512, max_extra_seq=3403 2023-06-15 13:15:01.416769: W external/org_tensorflow/tensorflow/compiler/xla/service/gpu/nvptx_compiler.cc:497] The NVIDIA driver's CUDA version is 12.0 which is older than the ptxas CUDA version (12.1.105). Because the driver is older than the ptxas version, XLA is disabling parallel compilation, which may slow down compilation. You should update your NVIDIA driver or use the NVIDIA-provided CUDA forward compatibility packages.

Can you please help about how I can fix these messages.

Thank you, Janos

Computational environment

• OS: [e.g. Ubuntu 22.04, Windows10 & WSL2, macOS...]
• CUDA version: nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA Corporation Built on Mon_Apr__3_17:16:06_PDT_2023 Cuda compilation tools, release 12.1, V12.1.105 Build cuda_12.1.r12.1/compiler.32688072_0

To Reproduce Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Expected behavior A clear and concise description of what you expected to happen.