mirror of
https://github.com/cloudstack-llc/mlx-knife.git
synced 2026-07-01 20:44:14 -04:00
The BROKE Cluster Team
bf7480d042
Major Features: - Audio transcription via mlx-audio backend (Whisper, >10min duration) - OpenAI /v1/audio/transcriptions endpoint - Memory Gate System (Vision: 8GB, Audio: 4GB) - Config-based backend routing (ADR-020) - Benchmark toolchain (memmon/memplot, Schema v0.2.2) Key Fixes: - EuroLLM tokenizer decoding - Vision-model text-only routing regression - Multimodal model context length detection - Memory cleanup bug (mx.metal.clear_cache) - Orphan process bug Test Results: - Unit tests: 647 passed, 11 skipped (Python 3.10-3.12) - wet-umbrella: 171 passed total See CHANGELOG.md for complete details and known issues.
20 lines
595 B
Plaintext
20 lines
595 B
Plaintext
# mlx_knife requirements
|
|
# Core dependencies for HuggingFace model management
|
|
|
|
huggingface-hub>=1.3.0
|
|
requests>=2.32.0
|
|
mlx-lm>=0.30.5 # Vision/Audio extras require 0.30.5+
|
|
mlx>=0.30.0 # Core MLX library
|
|
# Note: transformers pinned by mlx-lm (5.0.0rc3 as of 0.30.5)
|
|
# Known issue: trust_remote_code dialog affects some models (Klear-46B)
|
|
|
|
# API Server dependencies (for 'mlxk server' command)
|
|
fastapi>=0.116.0
|
|
uvicorn>=0.35.0
|
|
pydantic>=2.11.0
|
|
|
|
# Test dependencies (for FastAPI TestClient)
|
|
httpx>=0.27.0
|
|
|
|
# Note: Python 3.9-3.14 supported, tested on Apple Silicon M1/M2/M3/M4
|