Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Prostt5 ctranslate2 splitting long sequenes #327

Open
wants to merge 23 commits into
base: prostt5-ctranslate2
Choose a base branch
from
Open

Prostt5 ctranslate2 splitting long sequenes #327

wants to merge 23 commits into from

Commits on Aug 6, 2024

  1. developed draft workflow for splitting sequences bevore prostt5 predi… 

    …ction
    Marcus Wagner committed Aug 6, 2024
    Configuration menu
    Copy the full SHA
    04eae16 View commit details
    Browse the repository at this point in the history

Commits on Aug 9, 2024

  1. splitting of long sequences compiles and runs, but there is a sequenc… 

    …e length bug in the 3Di predictions
    Marcus Wagner committed Aug 9, 2024
    Configuration menu
    Copy the full SHA
    54037a7 View commit details
    Browse the repository at this point in the history

  2. fixed length mismatch of predicted 3Di seqs

    Marcus Wagner committed Aug 9, 2024
    Configuration menu
    Copy the full SHA
    e1daa14 View commit details
    Browse the repository at this point in the history

  3. cleaning up comments from debugging

    Marcus Wagner committed Aug 9, 2024
    Configuration menu
    Copy the full SHA
    410ef5e View commit details
    Browse the repository at this point in the history

  4. testing README and data

    Marcus Wagner committed Aug 9, 2024
    Configuration menu
    Copy the full SHA
    be0f5e9 View commit details
    Browse the repository at this point in the history

Commits on Aug 12, 2024

  1. added splitting parameter with max 6000 lenth

    Marcus Wagner committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    0eb6d3a View commit details
    Browse the repository at this point in the history

  2. removing limit of 6000 for split parameter

    Marcus Wagner committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    855695a View commit details
    Browse the repository at this point in the history

  3. creating minimal conda env for CUDA compiling

    Marcus Wagner committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    9d50e47 View commit details
    Browse the repository at this point in the history

Commits on Aug 13, 2024

  1. renamed cuda developement environment

    Marcus Wagner committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    893f0ba View commit details
    Browse the repository at this point in the history

  2. renamed long AA fasta, added second split test for 6000 length splits

    Marcus Wagner committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    bb311b6 View commit details
    Browse the repository at this point in the history

  3. creating minimal conda env

    Marcus Wagner committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    f8cb484 View commit details
    Browse the repository at this point in the history

  4. disableing thread affinity due to std::runtime_error thrown when test… 

    …ing splitting functionality
    Marcus Wagner committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    0f89180 View commit details
    Browse the repository at this point in the history

  5. gitignore file for build, test, and other dev folders

    Marcus Wagner committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    d9bcf69 View commit details
    Browse the repository at this point in the history

  6. polishing README

    Marcus Wagner committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    0ce2b87 View commit details
    Browse the repository at this point in the history

Commits on Aug 14, 2024

  1. updating test data for 6000 split length case

    Marcus Wagner committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    69cf233 View commit details
    Browse the repository at this point in the history

  2. split specific length calculation for substring creation

    Marcus Wagner committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    cdf8fc7 View commit details
    Browse the repository at this point in the history

  3. eliminating MAX_SPLIT_LENGTH constant, by using the parameter multipl… 

    …e times
    Marcus Wagner committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    ddc4ef4 View commit details
    Browse the repository at this point in the history

  4. final working tests

    Marcus Wagner committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    ea1f534 View commit details
    Browse the repository at this point in the history

Commits on Aug 21, 2024

  1. foldseek paper benchmark for ctranslate2 splitting branch

    Marcus Wagner committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    63ce4dc View commit details
    Browse the repository at this point in the history

Commits on Aug 22, 2024

  1. enabling CUDA for ProstT5

    Marcus Wagner committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    34d6b15 View commit details
    Browse the repository at this point in the history

  2. working on split length benchmark for foldseek ctranslate2

    Marcus Wagner committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    5a4801b View commit details
    Browse the repository at this point in the history

  3. foldseek crashed with CUDA enabled for ProstT5; currently debugging

    Marcus Wagner committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    db7baf9 View commit details
    Browse the repository at this point in the history

  4. rocx files for benchmarking; these are wrongly scaled, need to recomp… 

    …ute once CUDA build is fixed
    Marcus Wagner committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    fc2fcbf View commit details
    Browse the repository at this point in the history