Change sub-quad chunk threshold to use percentage

This commit is contained in:
brkirch
2023-01-06 01:01:51 -05:00
parent b119815333
commit b95a4c0ce5
2 changed files with 10 additions and 10 deletions

View File

@@ -59,7 +59,7 @@ parser.add_argument("--opt-split-attention", action='store_true', help="force-en
parser.add_argument("--opt-sub-quad-attention", action='store_true', help="enable memory efficient sub-quadratic cross-attention layer optimization")
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-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-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("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")