bentoml/BentoML v1.0.4

BentoML - v1.0.4

on GitHub

🍱 BentoML v1.0.4 is here!

• Added support for explicit GPU mapping for runners. In addition to specifying the number of GPU devices allocated to a runner, we can map a list of device IDs directly to a runner through configuration.

  runners:
    iris_clf_1:
      resources:
        nvidia.com/gpu: [2, 4] # Map device 2 and 4 to iris_clf_1 runner
    iris_clf_2:
      resources:
        nvidia.com/gpu: [1, 3] # Map device 1 and 3 to iris_clf_2 runner

• Added SSL support for API server through both CLI and configuration.

    --ssl-certfile TEXT          SSL certificate file
    --ssl-keyfile TEXT           SSL key file
    --ssl-keyfile-password TEXT  SSL keyfile password
    --ssl-version INTEGER        SSL version to use (see stdlib 'ssl' module)
    --ssl-cert-reqs INTEGER      Whether client certificate is required (see stdlib 'ssl' module)
    --ssl-ca-certs TEXT          CA certificates file
    --ssl-ciphers TEXT           Ciphers to use (see stdlib 'ssl' module)

• Added adaptive batching size histogram metrics, BENTOML_{runner}_{method}_adaptive_batch_size_bucket, for observability of batching mechanism details.

  

• Added support OpenTelemetry OTLP exporter for tracing and configures the OpenTelemetry resource automatically if user has not explicitly configured it through environment variables. Upgraded OpenTelemetry python packages to version 0.33b0.

  

• Added support for saving external_modules alongside with models in the save_model API. Saving external Python modules is useful for models with external dependencies, such as tokenizers, preprocessors, and configurations.

• Enhanced Swagger UI to include additional documentation and helper links.

  

💡 We continue to update the documentation on every release to help our users unlock the full power of BentoML.

• Checkout the adaptive batching documentation on how to leverage batching to improve inference latency and efficiency.
• Checkout the runner configuration documentation on how to customize resource allocation for runners at run time.

🙌 We continue to receive great engagement and support from the BentoML community.

• Shout out to @sptowey for their contribution on adding SSL support.
• Shout out to @dbuades for their contribution on adding the OTLP exporter.
• Shout out to @tweeklab for their contribution on fixing a bug on import_model in the MLflow framework.

What's Changed

• refactor: cli to bentoml_cli by @sauyon in #2880
• chore: remove typing-extensions dependency by @sauyon in #2879
• fix: remove chmod install scripts by @aarnphm in #2830
• fix: relative imports to lazy by @aarnphm in #2882
• fix(cli): click utilities imports by @aarnphm in #2883
• docs: add custom model runner example by @parano in #2885
• qa: analytics unit tests by @aarnphm in #2878
• chore: script for releasing quickstart bento by @parano in #2892
• fix: pushing models from Bento instead of local modelstore by @parano in #2887
• fix(containerize): supports passing multiple tags by @aarnphm in #2872
• feat: explicit GPU runner mappings by @jjmachan in #2862
• fix: setuptools doesn't include bentoml_cli by @bojiang in #2898
• feat: Add SSL support for http api servers via bentoml serve by @sptowey in #2886
• patch: ssl styling and default value check by @aarnphm in #2899
• fix(scheduling): raise an error for invalid resources by @bojiang in #2894
• chore(templates): cleanup debian dependency logic by @aarnphm in #2904
• fix(ci): unittest failed by @bojiang in #2908
• chore(cli): add figlet for CLI by @aarnphm in #2909
• feat: codespace by @aarnphm in #2907
• feat: use yatai proxy to upload/download bentos/models by @yetone in #2832
• fix(scheduling): numpy worker environs are not taking effect by @bojiang in #2893
• feat: Adaptive batching size histogram metrics by @ssheng in #2902
• chore(swagger): include help links by @parano in #2927
• feat(tracing): add support for otlp exporter by @dbuades in #2918
• chore: Lock OpenTelemetry versions and add tracing metadata by @ssheng in #2928
• revert: unminify CSS by @aarnphm in #2931
• fix: importing mlflow:/ urls with no extra path info by @tweeklab in #2930
• fix(yatai): make presigned_urls_deprecated optional by @bojiang in #2933
• feat: add timeout option for bentoml runner config by @jjmachan in #2890
• perf(cli): speed up by @aarnphm in #2934
• chore: remove multipart IO descriptor warning by @ssheng in #2936
• fix(json): revert eager check by @aarnphm in #2926
• chore: remove --config flag to load the bentoml runtime config by @jjmachan in #2939
• chore: update README messaging by @ssheng in #2937
• fix: use a temporary file for file uploads by @sauyon in #2929
• feat(cli): add CLI command to serve a runner by @bojiang in #2920
• docs: Runner configuration for batching and resource allocation by @ssheng in #2941
• bug: handle bad image file by @parano in #2942
• chore(docs): earlier check for buildx by @aarnphm in #2940
• fix(cli): helper message default values by @ssheng in #2943
• feat(sdk): add external_modules option to save_model by @bojiang in #2895
• fix(cli): component name regression by @ssheng in #2944

New Contributors

• @sptowey made their first contribution in #2886
• @dbuades made their first contribution in #2918
• @tweeklab made their first contribution in #2930

Full Changelog: v1.0.3...v1.0.4