WildAi 2fc53b85a3 fix: version-safe config dtype access — silence torch_dtype deprecation (v2.7.1) ...

transformers 5.x deprecated PretrainedConfig.torch_dtype; both getter and setter log a warning on every load. Add set_config_dtype/get_config_dtype helpers (configuration_vibevoice.py + modules/dtype_utils.py) that use config.dtype on v5 and torch_dtype on 4.x, and route the loader/external_loader writes plus the 5 vendored modeling reader blocks through them. +17 regression tests incl. no-warning assertions on the real load path.

2026-08-27 21:49:17 +03:00

..

__init__.py

major refactoring

2025-09-10 12:06:26 +03:00

asr_generation.py

feat: unload-on-change eviction + quant-resident runtime for GGUF and quantized safetensors (v2.4.0 -> v2.5.0)

2026-08-26 12:17:24 +03:00

asr_loader.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

attention_utils.py

refactor init

2026-08-14 20:26:31 +03:00

audio_backend.py

feat: torchaudio-primary audio backend, librosa now optional (v2.1.0)

2026-08-15 21:54:53 +03:00

audio_utils.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

base_loader.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

comfy_stream.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

config_detect.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

convrot_quant.py

feat: native lowvram streaming for oversized models (v2.6.0)

2026-08-27 17:52:17 +03:00

custom_types.py

feat: external model input via VibeVoiceLoadExternalModel node (v2.2.0)

2026-08-16 23:59:04 +03:00

device_utils.py

refactor init

2026-08-14 20:26:31 +03:00

dtype_utils.py

fix: version-safe config dtype access — silence torch_dtype deprecation (v2.7.1)

2026-08-27 21:49:17 +03:00

external_loader.py

fix: version-safe config dtype access — silence torch_dtype deprecation (v2.7.1)

2026-08-27 21:49:17 +03:00

generation.py

feat: native lowvram streaming for oversized models (v2.6.0)

2026-08-27 17:52:17 +03:00

gguf_quant.py

feat: native lowvram streaming for oversized models (v2.6.0)

2026-08-27 17:52:17 +03:00

loader.py

fix: version-safe config dtype access — silence torch_dtype deprecation (v2.7.1)

2026-08-27 21:49:17 +03:00

model_info.py

fix: lowvram partial-load completion, VibeVoice-7B rename follow-through, copy-free packaged tokenizer

2026-08-26 13:24:55 +03:00

model_registry.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

patcher.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

quant_common.py

feat: auto-detect config_name, drop VibeVoice-Large (v2.7.0)

2026-08-27 20:33:19 +03:00

utils.py

refactor init

2026-08-14 20:26:31 +03:00

vendor_streaming_types.py

feat: native lowvram streaming for oversized models (v2.6.0)

2026-08-27 17:52:17 +03:00