Billy D. 297b0d8ebd fix: move mlflow import inside __init__ to avoid cloudpickle serialization failure ...

The strixhalo LLM worker uses py_executable which bypasses pip runtime_env.
Module-level try/except still fails because cloudpickle on the head node
resolves the real InferenceLogger class and serializes a module reference.
Moving the import inside __init__ means it runs at actor construction time
on the worker, where ImportError is caught gracefully.

2026-02-12 07:06:49 -05:00

..

__init__.py

feat: initial ray-serve-apps PyPI package

2026-02-03 07:03:39 -05:00

mlflow_logger.py

feat: add MLflow inference logging to all Ray Serve apps

2026-02-12 06:14:30 -05:00

py.typed

feat: initial ray-serve-apps PyPI package

2026-02-03 07:03:39 -05:00

serve_embeddings.py

fix: make mlflow_logger import optional with no-op fallback

2026-02-12 07:01:17 -05:00

serve_llm.py

fix: move mlflow import inside __init__ to avoid cloudpickle serialization failure

2026-02-12 07:06:49 -05:00

serve_reranker.py

fix: make mlflow_logger import optional with no-op fallback

2026-02-12 07:01:17 -05:00

serve_tts.py

fix: make mlflow_logger import optional with no-op fallback

2026-02-12 07:01:17 -05:00

serve_whisper.py

fix: make mlflow_logger import optional with no-op fallback

2026-02-12 07:01:17 -05:00