fix(RCLane) : fix option parallel mode

feat(RCLane): archive parallel BEV projection modes

feat(RCLane): switch to C++ for runtime modeling

fix(RCLane): stabilize lane decode and ONNX inference

fix(RCLane): persist GT cache in HF bucket

perf(RCLane): bound and cache F1 lane decoding

perf(RCLane): saturate dual H200 train and eval

perf(RCLane): speed up CARLA F1 eval ~14x (downscaled IoU + cached masks)

chore(RCLane): add HF Jobs runner for CARLA (Space code + F1 eval + per-epoch upload)

feat(RCLane): add resume, F1 eval, full logging & per-epoch HF upload for CARLA

feat(RCLane): add CARLA dataset

feat(RCLane): add PyTorch port of RCLane

Initial commit