PyPI page
Home page
Author:
kiarina
Summary:
Unified local inference API server for LLM agents on Apple Silicon (MLX): chat, embedding, image, music, sound-effect, and video — one process, one global memory budget, one single-flight queue, unified jobs and files.
Latest version:
0.8.0
Required dependencies:
click
|
fastapi
|
httpx
|
kiarina-utils-app
|
kiarina-utils-common
|
mflux
|
mlx-audiocraft
|
mlx-embeddings
|
mlx-lm
|
mlx-vlm
|
numpy
|
pillow
|
psutil
|
pydantic
|
pydantic-settings-manager
|
python-multipart
|
pyyaml
|
questionary
|
soundfile
|
torch
|
torchaudio
|
torchvision
|
uvicorn
Downloads last day:
1
Downloads last week:
25
Downloads last month:
290
7-day smoothing