Add ONNX files for per-arch TRT compilation

Drop L-range suffix from SAME-L decoder filename

Reorganize tensorRT/ into per-arch subdirs; rebuild DiT engines with conditioner baked in

Remove padding_embedding.pt — these ship with the inference code repo

Remove pipeline_state from tensorRT/ — it ships with the inference code repo, not here

Add pipeline_state + per-model padding_embedding for SA3 TRT pipeline

Add MLX weights for SA3 inference

Add SA3 TRT engines (LFS-tracked)

Create MLX/README.md

Create tensorRT/README.md

Update model card

Update model card

Update model card

Update model card

Add tags and base_model metadata

Add logo

Add NOTICE

Add LICENSE_GEMMA.md

Add LICENSE.md

Update model card

initial commit