PyPI page
Home page
Author:
mlx-serve contributors
Summary:
Local inference server for Apple Silicon that hot-swaps MLX models (LLM, vision, embeddings, TTS, STT) via OpenAI-compatible API
Latest version:
0.3.0
Required dependencies:
fastapi
|
httpx
|
psutil
|
python-multipart
|
pyyaml
|
uvicorn
Optional dependencies:
laya-mlx
|
mlx-audio
|
mlx-embeddings
|
mlx-lm
|
mlx-vlm
|
mlx-whisper
|
pytest
|
pytest-asyncio
|
ruff
Downloads last day:
10
Downloads last week:
155
Downloads last month:
357
7-day smoothing