Billy D. f66de251eb fix: add ENFORCE_EAGER env var to skip torch.compile on ROCm ...

torch._dynamo.exc.Unsupported crashes EngineCore during graph tracing
of LlamaDecoderLayer on gfx1151.  ENFORCE_EAGER=true bypasses
torch.compile and CUDA graph capture entirely.

2026-02-13 06:56:29 -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: add ENFORCE_EAGER env var to skip torch.compile on ROCm

2026-02-13 06:56:29 -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