feat: Add GPU-specific Ray worker images with CI/CD
- Add Dockerfiles for nvidia, rdna2, strixhalo, and intel GPU targets - Add ray-serve modules (embeddings, whisper, tts, llm, reranker) - Add Gitea Actions workflow for automated builds - Add Makefile for local development - Update README with comprehensive documentation
This commit is contained in:
24
ray-serve/requirements.txt
Normal file
24
ray-serve/requirements.txt
Normal file
@@ -0,0 +1,24 @@
|
||||
# Ray Serve dependencies
|
||||
ray[serve]==2.53.0
|
||||
|
||||
# LLM inference
|
||||
vllm
|
||||
|
||||
# Embeddings and reranking
|
||||
sentence-transformers
|
||||
|
||||
# Speech-to-text
|
||||
faster-whisper
|
||||
|
||||
# Text-to-speech
|
||||
TTS
|
||||
|
||||
# HTTP client
|
||||
httpx
|
||||
|
||||
# Numerical computing
|
||||
numpy
|
||||
scipy
|
||||
|
||||
# Optional: Intel GPU support (for danilo node)
|
||||
# intel-extension-for-pytorch
|
||||
Reference in New Issue
Block a user