feat: initial ray-serve-apps PyPI package
Some checks failed
Build and Publish ray-serve-apps / lint (push) Failing after 11m2s
Build and Publish ray-serve-apps / publish (push) Has been cancelled

Implements ADR-0024: Ray Repository Structure

- Ray Serve deployments for GPU-shared AI inference
- Published as PyPI package for dynamic code loading
- Deployments: LLM, embeddings, reranker, whisper, TTS
- CI/CD workflow publishes to Gitea PyPI on push to main

Extracted from kuberay-images repo per ADR-0024
This commit is contained in:
2026-02-03 07:03:39 -05:00
parent eac8f27f2e
commit 8ef914ec12
11 changed files with 887 additions and 1 deletions

15
ray_serve/__init__.py Normal file
View File

@@ -0,0 +1,15 @@
# Ray Serve deployments for GPU-shared AI inference
# Published to Gitea PyPI as ray-serve-apps
from ray_serve.serve_embeddings import app as embeddings_app
from ray_serve.serve_llm import app as llm_app
from ray_serve.serve_reranker import app as reranker_app
from ray_serve.serve_tts import app as tts_app
from ray_serve.serve_whisper import app as whisper_app
__all__ = [
"embeddings_app",
"llm_app",
"reranker_app",
"tts_app",
"whisper_app",
]