Ethanfel 89d6fccd28 debug: add per-operation VRAM logging in first training step ...

Logs VRAM at: after target_mel, after vocoder forward, before loss,
after loss computation, and after backward. Only logs for step 0 to
avoid spam. Will identify which operation causes the 94 GiB spike.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-04-10 01:35:54 +02:00

..

__init__.py

fix: remove FlashSR (audiosr incompatible with Python 3.12), add training loss CSV

2026-04-09 17:18:34 +02:00

selva_activation_steering_extractor.py

feat(steering): conditional-only injection + per-position vectors

2026-04-09 01:02:51 +02:00

selva_activation_steering_loader.py

feat: add activation steering pipeline (extractor, loader, sampler injection)

2026-04-09 00:38:26 +02:00

selva_audio_postprocess.py

fix: remove FlashSR (audiosr incompatible with Python 3.12), add training loss CSV

2026-04-09 17:18:34 +02:00

selva_audio_preprocessors.py

feat: add SelVA HF Smoother and Spectral Matcher preprocessing nodes

2026-04-08 20:28:16 +02:00

selva_bigvgan_loader.py

fix: move vocoder to correct device after GAFilter injection

2026-04-09 20:28:55 +02:00

selva_bigvgan_trainer.py

debug: add per-operation VRAM logging in first training step

2026-04-10 01:35:54 +02:00

selva_dataset_browser.py

feat: thorough overnight sweep + dataset browser updates

2026-04-08 00:38:19 +02:00

selva_dataset_pipeline.py

feat: add SelvaDatasetCompressor node for parallel compression

2026-04-09 15:36:27 +02:00

selva_ditto_optimizer.py

fix: correct DITTO reference latent space mismatch

2026-04-09 18:57:08 +02:00

selva_feature_extractor.py

fix: set OUTPUT_NODE=True on SelVA Feature Extractor so it runs without connected outputs

2026-04-06 00:11:16 +02:00

selva_lora_evaluator.py

feat: PiSSA init, rsLoRA scaling, Spectral Surgery, and training fixes

2026-04-09 21:54:36 +02:00

selva_lora_loader.py

feat: PiSSA init, rsLoRA scaling, Spectral Surgery, and training fixes

2026-04-09 21:54:36 +02:00

selva_lora_scheduler.py

feat: add PiSSA/rsLoRA support to scheduler and PiSSA sweep experiment

2026-04-09 22:07:27 +02:00

selva_lora_trainer.py

feat: PiSSA init, rsLoRA scaling, Spectral Surgery, and training fixes

2026-04-09 21:54:36 +02:00

selva_model_loader.py

fix: enable VAE encoder in model loader — required for DITTO reference encoding

2026-04-09 18:15:27 +02:00

selva_sampler.py

feat(steering): conditional-only injection + per-position vectors

2026-04-09 01:02:51 +02:00

selva_skip_experiment.py

feat: SelVA Skip Experiment node + save partial scalars on skip

2026-04-08 13:10:43 +02:00

selva_textual_inversion_loader.py

feat: add inject_mode (suffix/prefix) to TI pipeline

2026-04-08 23:31:52 +02:00

selva_textual_inversion_trainer.py

fix: move only VAE+vocoder to GPU during eval to prevent device mismatch

2026-04-09 19:36:02 +02:00

selva_ti_scheduler.py

fix(ti): lower default lr/batch, add lr_batch sweep group

2026-04-08 23:42:22 +02:00

selva_vae_roundtrip.py

fix: move only VAE+vocoder to GPU during eval to prevent device mismatch

2026-04-09 19:36:02 +02:00

utils.py

chore: remove all PrismAudio code from main branch

2026-04-04 17:58:31 +02:00