mirror of
https://github.com/cloudstack-llc/mlx-knife.git
synced 2026-07-22 02:25:23 -04:00
The BROKE Cluster Team
ce46601d9d
• MXFP4 Quantization Support (MLX ≥0.29.0, MLX-LM ≥0.27.0) • GPT-OSS Reasoning Models with --hide-reasoning flag • Enhanced Show Command with improved quantization display • Documentation updates (README.md, TESTING.md) See CHANGELOG.md for complete technical details. Partial Issue #32 (GPT-OSS only, other reasoning models remain open).
14 lines
388 B
Plaintext
14 lines
388 B
Plaintext
# mlx_knife requirements
|
|
# Core dependencies for HuggingFace model management
|
|
|
|
huggingface-hub>=0.34.0
|
|
requests>=2.32.0
|
|
mlx-lm>=0.27.0 # For running MLX models with streaming support
|
|
mlx>=0.29.0 # Core MLX library
|
|
|
|
# API Server dependencies (for 'mlxk server' command)
|
|
fastapi>=0.116.0
|
|
uvicorn>=0.35.0
|
|
pydantic>=2.11.0
|
|
|
|
# Note: Python 3.9+ supported, tested on Apple Silicon M1/M2/M3 |