poxularandCursor d101418eb9 Add separate CUDA ONNX path for experimental GPU inference. ...

Keeps CPU parity nodes and providers unchanged; CUDA modules and ComfyUI
nodes run alongside with CPU fallback when CUDA EP is unavailable.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-06-02 00:22:25 +02:00

..

bench_cuda_vs_cpu.py

Add separate CUDA ONNX path for experimental GPU inference.

2026-06-02 00:22:25 +02:00

convert_face_models_to_onnx.py

Bundle face ONNX models and probe-parity pipeline for ComfyUI git pull.

2026-06-01 18:26:38 +02:00

parity_pair.py

Fix probe parity net feed and verify lut_hash golden target.

2026-06-01 22:46:45 +02:00

requirements-convert.txt

Bundle face ONNX models and probe-parity pipeline for ComfyUI git pull.

2026-06-01 18:26:38 +02:00