parser.add_argument("--sub-quad-q-chunk-size",type=int,help="query chunk size for the sub-quadratic cross-attention layer optimization to use",default=1024)
parser.add_argument("--sub-quad-q-chunk-size",type=int,help="query chunk size for the sub-quadratic cross-attention layer optimization to use",default=1024)
parser.add_argument("--sub-quad-kv-chunk-size",type=int,help="kv chunk size for the sub-quadratic cross-attention layer optimization to use",default=None)
parser.add_argument("--sub-quad-kv-chunk-size",type=int,help="kv chunk size for the sub-quadratic cross-attention layer optimization to use",default=None)
parser.add_argument("--sub-quad-chunk-threshold",type=int,help="the size threshold in bytes for the sub-quadratic cross-attention layer optimization to use chunking",default=None)
parser.add_argument("--sub-quad-chunk-threshold",type=int,help="the percentage of VRAM threshold for the sub-quadratic cross-attention layer optimization to use chunking",default=None)
parser.add_argument("--opt-split-attention-invokeai",action='store_true',help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
parser.add_argument("--opt-split-attention-invokeai",action='store_true',help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
parser.add_argument("--opt-split-attention-v1",action='store_true',help="enable older version of split attention optimization that does not consume all the VRAM it can find")
parser.add_argument("--opt-split-attention-v1",action='store_true',help="enable older version of split attention optimization that does not consume all the VRAM it can find")