andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Integrate RAM cache with model RAM management (#13173)

Browse Source
This commit is contained in:
rattus
2026-03-27 18:34:16 -07:00
committed by GitHub
parent 3696c5bad6
commit b353a7c863
9 changed files with 61 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
comfy/cli_args.py
+3 -1
View File
@@ -110,11 +110,13 @@ parser.add_argument("--preview-method", type=LatentPreviewMethod, default=Latent
parser.add_argument("--preview-size", type=int, default=512, help="Sets the maximum preview size for sampler nodes.")
CACHE_RAM_AUTO_GB = -1.0
cache_group = parser.add_mutually_exclusive_group()
cache_group.add_argument("--cache-classic", action="store_true", help="Use the old style (aggressive) caching.")
cache_group.add_argument("--cache-lru", type=int, default=0, help="Use LRU caching with a maximum of N node results cached. May use more RAM/VRAM.")
cache_group.add_argument("--cache-none", action="store_true", help="Reduced RAM/VRAM usage at the expense of executing every node for each run.")
cache_group.add_argument("--cache-ram", nargs='?', const=4.0, type=float, default=0, help="Use RAM pressure caching with the specified headroom threshold. If available RAM drops below the threhold the cache remove large items to free RAM. Default 4GB")
cache_group.add_argument("--cache-ram", nargs='?', const=CACHE_RAM_AUTO_GB, type=float, default=0, help="Use RAM pressure caching with the specified headroom threshold. If available RAM drops below the threshold the cache removes large items to free RAM. Default (when no value is provided): 25%% of system RAM (min 4GB, max 32GB).")
attn_group = parser.add_mutually_exclusive_group()
attn_group.add_argument("--use-split-cross-attention", action="store_true", help="Use the split cross attention optimization. Ignored when xformers is used.")