add --high-ram option (#14437)

Add this option for users who know they have so much ram they want
to pin everything or have a pagefile that outruns their disk speed.

The removes the RAM pressure caps completely and pins behind the
primary model load forcing all models to be permanently comitted
to RAM.

comfy/cli_args.py

@@ -115,6 +115,7 @@ cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metav
 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("--high-ram", action="store_true", help="Can improve performance slightly on high RAM or on systems where pagefile use is preferred over model loading.")
 
 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.")
@@ -249,6 +250,9 @@ else:
 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.high_ram:
+    args.cache_classic = True
+
 if args.windows_standalone_build:
     args.auto_launch = True
 

comfy/model_management.py

@@ -643,6 +643,8 @@ def free_pins(size, evict_active=False):
     return freed_total
 
 def ensure_pin_budget(size, evict_active=False):
+    if args.high_ram:
+        return True
     if args.fast_disk:
         shortfall = TOTAL_PINNED_MEMORY + size - MAX_PINNED_MEMORY
     else:
@@ -1496,6 +1498,8 @@ if not args.disable_pinned_memory:
 PINNING_ALLOWED_TYPES = set(["Tensor", "Parameter", "QuantizedTensor"])
 
 def pinned_hostbuf_size(size):
+    if args.high_ram:
+        return max(0, int(size * 2))
     return max(0, int(min(size, MAX_PINNED_MEMORY) * 2))
 
 def discard_cuda_async_error():

comfy/ops.py

@@ -180,7 +180,7 @@ def cast_modules_with_vbar(comfy_modules, dtype, device, bias_dtype, non_blockin
             if pin is not None:
                 cast_maybe_lowvram_patch([pin], dest, offload_stream)
                 return
-            if signature is None:
+            if signature is None or args.high_ram:
                 comfy.pinned_memory.pin_memory(m, subset=subset, size=size)
                 pin = comfy.pinned_memory.get_pin(m, subset=subset)
             cast_maybe_lowvram_patch(source, pin, offload_stream, xfer_dest2=dest)