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

Quantized checkpoint support in export and deploy modules #8859

Merged
merged 19 commits into from
Apr 23, 2024
Merged

Quantized checkpoint support in export and deploy modules #8859

merged 19 commits into from
Apr 23, 2024

Commits on Apr 5, 2024

  1. Resolve engine build command for int8_sq quantization 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    22085ad View commit details
    Browse the repository at this point in the history

  2. Fix links and typos 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    88850ae View commit details
    Browse the repository at this point in the history

  3. Add quantization docs to ToC 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    1c70b6c View commit details
    Browse the repository at this point in the history

  4. Opt for using torchrun 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 5, 2024
    Configuration menu
    Copy the full SHA
    c5e0b97 View commit details
    Browse the repository at this point in the history

Commits on Apr 9, 2024

  1. Enable exporting and running quantized qnemo checkpoints 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 9, 2024
    Configuration menu
    Copy the full SHA
    e2d23a3 View commit details
    Browse the repository at this point in the history

  2. Report evaluation time and shorten passing results around 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 9, 2024
    Configuration menu
    Copy the full SHA
    097c3c2 View commit details
    Browse the repository at this point in the history

  3. Fix undefined model_info 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 9, 2024
    Configuration menu
    Copy the full SHA
    3db0751 View commit details
    Browse the repository at this point in the history

  4. [pre-commit.ci] auto fixes from pre-commit.com hooks 

    for more information, see https://pre-commit.ci
    @pre-commit-ci
    pre-commit-ci[bot] committed Apr 9, 2024
    Configuration menu
    Copy the full SHA
    b2eca1a View commit details
    Browse the repository at this point in the history

Commits on Apr 10, 2024

  1. Unfold import path 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 10, 2024
    Configuration menu
    Copy the full SHA
    51d87ce View commit details
    Browse the repository at this point in the history

  2. Quantization docs update 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 10, 2024
    Configuration menu
    Copy the full SHA
    fb79e77 View commit details
    Browse the repository at this point in the history

  3. Enable HF tokenizer 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 10, 2024
    Configuration menu
    Copy the full SHA
    1e3f607 View commit details
    Browse the repository at this point in the history

  4. [pre-commit.ci] auto fixes from pre-commit.com hooks 

    for more information, see https://pre-commit.ci
    @pre-commit-ci
    pre-commit-ci[bot] committed Apr 10, 2024
    Configuration menu
    Copy the full SHA
    2fdcbf6 View commit details
    Browse the repository at this point in the history

  5. Merge branch 'main' into jlasek/qnemo_support

    @janekl
    janekl authored Apr 10, 2024
    Configuration menu
    Copy the full SHA
    566723d View commit details
    Browse the repository at this point in the history

  6. Add copyright headers 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 10, 2024
    Configuration menu
    Copy the full SHA
    a6506cc View commit details
    Browse the repository at this point in the history

Commits on Apr 19, 2024

  1. Update AMMO to 0.9.4 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    09ddf39 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into jlasek/qnemo_support 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    b35298e View commit details
    Browse the repository at this point in the history

  3. Unpack qnemo checkpoint if it's a tarball 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    a937445 View commit details
    Browse the repository at this point in the history

  4. Format results display 

    Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
    @janekl
    janekl committed Apr 19, 2024
    Configuration menu
    Copy the full SHA
    6520d1f View commit details
    Browse the repository at this point in the history

Commits on Apr 22, 2024

  1. Merge branch 'main' into jlasek/qnemo_support

    @ericharper
    ericharper authored Apr 22, 2024
    Configuration menu
    Copy the full SHA
    e4835eb View commit details
    Browse the repository at this point in the history