3 people 624f6a2140 fix(tada): run voice-prompt encode under torch.inference_mode (#955) ...

Encoder.eval() alone still builds an autograd graph because parameters
require grad by default. On 8GB GPUs that ballooned TADA encode VRAM far
past the model footprint (issue 890). Wrap the encode forward in
inference_mode and add a unit test that asserts the flag is set.

Co-authored-by: fooSynaptic <[email protected]>

2026-07-26 23:31:20 -07:00

..

__init__.py

feat: 0.5.0 Capture release — dictation, MCP, personalities (#544)

2026-04-25 15:46:35 -07:00

base.py

feat(windows): Native AMD ROCm GPU Acceleration (Resolves #531) (#538)

2026-06-30 15:43:18 -07:00

chatterbox_backend.py

fix: complete Intel XPU support — device-aware seeding, GPU status reporting, and setup detection

2026-03-18 17:01:12 -07:00

chatterbox_turbo_backend.py

fix: complete Intel XPU support — device-aware seeding, GPU status reporting, and setup detection

2026-03-18 17:01:12 -07:00

hume_backend.py

fix(tada): run voice-prompt encode under torch.inference_mode (#955)

2026-07-26 23:31:20 -07:00

kokoro_backend.py

fix(kokoro): add missing male Mandarin voices (#788)

2026-07-20 20:51:06 -07:00

luxtts_backend.py

fix: complete Intel XPU support — device-aware seeding, GPU status reporting, and setup detection

2026-03-18 17:01:12 -07:00

mlx_backend.py

fix(offline): patch transformers mistral-regex check to survive HF failures (#530)

2026-04-21 22:01:29 -07:00

pytorch_backend.py

fix(offline): patch transformers mistral-regex check to survive HF failures (#530)

2026-04-21 22:01:29 -07:00

qwen_custom_voice_backend.py

fix(offline): patch transformers mistral-regex check to survive HF failures (#530)

2026-04-21 22:01:29 -07:00

qwen_llm_backend.py

fix(offline): remove process-global offline guard from Qwen3 LLM loads (#924)

2026-07-20 18:47:10 -07:00