update defaults: LR 3e-4, rank 32, alpha 2x rank (per Side-Step author)

save only on cancel/finish, max epochs 1000, default 3

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

allow custom LoRA values in dropdown (API clients)

log ace-server restart, show output for adapter debugging

fix: forward adapter to synth request, default LM to 1.7B

fix: adapter saved to clean dir, LM dropdown no 'Default', on-demand download

Side-Step training engine, tested locally on CPU

add LoRA adapter dropdown to inference UI

default mp3, remove format selector, increase LM timeout to 900s

remove accelerate (causes meta tensors), clean up patches

fix meta tensor crash: force low_cpu_mem_usage=False and float32 for CPU

disable flash_sdp on CPU, force attn_implementation=sdpa for training

add granular logging + full stderr to diagnose preprocessing hang

fix: use float32 not bfloat16 for CPU training (bf16 deadlocks on CPU)

redirect training subprocess stderr to log file for debugging

run training as detached subprocess to survive Gradio session timeout

use bfloat16 precision for training to halve RAM usage

stop ace-server during training to free RAM, restart after, add log visibility

monkey-patch torchaudio.load to use soundfile backend

add LoRA training, fix css kwarg

full app: CLI + Gradio + training placeholder + MCP

rewrite app.py for ace-server HTTP API, no torch

clickable title

slim title

compact grid UI, 4B default, show training model

force float32 on training model for CPU

fix: LoRA rank param is 'r' not 'rank'

fix training: use LoRAConfigV2 instead of Union type alias

step 7: real app.py

step 6: +numba (all deps)

step 5: +vector-quantize-pytorch

step 4: +peft +torchvision

step 3: core deps without heavy ones

step label

step 1: bare gradio