--attention-implementation not implemented

[AlDante]

Not sure if this is a code bug or I misunderstood the documentation. At any rate, attention-implementation is not a flag, despite the performance table suggesting otherwise.

time python -m python_coreml_stable_diffusion.pipeline --prompt "highly detailed photo of assistant professor getting lost in a data labyrinth with cobras and vipers" -i output-mlpackages -o images --compute-unit ALL --seed 93 --model-version runwayml/stable-diffusion-v1-5 --attention-implementation ORIGINAL
WARNING:coremltools:Torch version 1.13.0 has not been tested with coremltools. You may run into unexpected errors. Torch 1.12.1 is the most recent version that has been tested.
usage: pipeline.py [-h] --prompt PROMPT -i I -o O [--seed SEED] [--model-version MODEL_VERSION]
                   [--compute-unit {ALL,CPU_AND_GPU,CPU_ONLY,CPU_AND_NE}]
                   [--scheduler {DDIM,DPMSolverMultistep,EulerAncestralDiscrete,EulerDiscrete,LMSDiscrete,PNDM}]
                   [--num-inference-steps NUM_INFERENCE_STEPS]
pipeline.py: error: unrecognized arguments: --attention-implementation ORIGINAL
python -m python_coreml_stable_diffusion.pipeline --prompt  -i  -o images  AL  1.79s user 3.92s system 384% cpu 1.483 total