Merge remote-tracking branch 'origin/master' into worksplit-multigpu

Brings in 18 commits from master so worksplit-multigpu does not regress
fixes that landed on main since the last sync:

- #13699 Hunyuan 3D 2.1 batch-size fixes (overlap with our own backport;
  conflict resolved in favor of the shape>=2 gate that binds
  swap_cfg_halves once and reuses it for the output swap-back)
- #14031 ModelPatcherDynamic lora reshape / backup restore fix
- #13802 Multi-threaded model load (memory_management / pinned_memory /
  model_management / aimdo plumbing)
- #12679 lanczos single-channel tensor fix
- #14010 Stable Audio 3 support
- assorted partner-node, openapi, workflow-template, and tooling updates

Amp-Thread-ID: https://ampcode.com/threads/T-019e4a00-fe3d-76bd-a2f2-a8c8c4040082
Co-authored-by: Amp <amp@ampcode.com>

comfy/cli_args.py

@@ -110,13 +110,11 @@ 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-ram", nargs='*', type=float, default=[], metavar="GB", help="Use RAM pressure caching with the specified headroom thresholds. This is the default caching mode. The first value sets the active-cache threshold; the optional second value sets the inactive-cache/pin threshold. Defaults when no values are provided: active 25%% of system RAM (min 4GB, max 32GB), inactive 75%% of system RAM (min 12GB, max 96GB).")
 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=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.")
@@ -245,6 +243,9 @@ if comfy.options.args_parsing:
 else:
     args = parser.parse_args([])
 
+if args.cache_ram is not None and len(args.cache_ram) > 2:
+    parser.error("--cache-ram accepts at most two values: active GB and inactive GB")
+
 if args.windows_standalone_build:
     args.auto_launch = True