upgrade torch>=2.6 (CLAP needs torch.load fix for CVE-2025-32434)

remove lightning dep (not needed, breaks CPU torch index)

add fast captioning module (CLAP + faster-whisper + Silero VAD), update deps

remove XL checkpoint download (OOMKilled build, training uses standard turbo)

fix: save_every_n_epochs=0, add demucs-infer to Dockerfile, debug adapter dir

major update: PyTorch inference, Gradio 6, session isolation, /understand captioning

add auto-captioning (BPM/key/signature via librosa), add librosa+mutagen deps

switch training to standard turbo (11s/epoch), auto-select standard GGUF for LoRA inference

fix: train on XL turbo (matches XL GGUF for inference), add XL checkpoint download

copy train_engine.py into Docker image

Side-Step training engine, tested locally on CPU

switch back to 1.7B LM (fastest at 269s, 0.6B was 936s)

swap LM to 0.6B Q8_0 for speed test

swap LM 4B->1.7B Q8_0 for faster CPU inference

remove accelerate (causes meta tensors), clean up patches

add einops + vector_quantize_pytorch for model loading

pre-download training checkpoints at build time

pin diffusers==0.30.3 for torch 2.4.x compat

pin torchaudio==2.4.0 (before torchcodec default backend)

force uninstall torchcodec (torchaudio dependency, broken on Ubuntu 22.04)

remove torchcodec (needs FFmpeg 5.x), keep soundfile backend

add torchcodec + ffmpeg for torchaudio audio loading

add soundfile + libsndfile1 for torchaudio backend

add all training deps: diffusers lightning numpy tensorboard

add torchaudio dep for training preprocess

add loguru dep for training preprocess

install gradio[mcp] for mcp_server support

add git to runtime image for ace-step source clone

add LoRA training, fix css kwarg

copy all shared libs including versioned symlinks

add pkg-config for BLAS detection

switch to acestep.cpp GGUF: XL turbo Q4_K_M + 4B LM Q5_K_M