wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-05-25 08:27:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

Document --cuda-device comma format and MultiGPU Options relative_speed gap

Browse Source 
Two doc-only changes addressing minor CodeRabbit findings on PR #7063:

* cli_args.py: clarify --cuda-device help text to document the required comma-separated format ('0' or '0,1'), matching how the value is consumed by CUDA_VISIBLE_DEVICES in main.py.

* nodes_multigpu.py: add a docstring NOTE on the (currently unregistered) MultiGPUOptionsNode explaining that its relative_speed input is plumbed through to model_options['multigpu_options'] but is not yet consulted by the cond scheduler, which still uses uniform round-robin via next_available_device(). Wire relative_speed into the scheduler before re-enabling the node.

Amp-Thread-ID: https://ampcode.com/threads/T-019e43b8-8258-70fd-ab3a-53e4c97f85d5
Co-authored-by: Amp <amp@ampcode.com>
This commit is contained in:
Jedrzej Kosinski 2026-05-20 20:48:59 -07:00
parent ac0a90c323
commit 4d9106dced
2 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/cli_args.py
View File

@ -49,7 +49,7 @@ parser.add_argument("--temp-directory", type=str, default=None, help="Set the Co
parser.add_argument("--input-directory", type=str, default=None, help="Set the ComfyUI input directory. Overrides --base-directory.")
parser.add_argument("--auto-launch", action="store_true", help="Automatically launch ComfyUI in the default browser.")
parser.add_argument("--disable-auto-launch", action="store_true", help="Disable auto launching the browser.")
parser.add_argument("--cuda-device", type=str, default=None, metavar="DEVICE_ID", help="Set the ids of cuda devices this instance will use. All other devices will not be visible.")
parser.add_argument("--cuda-device", type=str, default=None, metavar="DEVICE_ID", help="Set the ids of cuda devices this instance will use, as a comma-separated list (e.g. '0' or '0,1'). All other devices will not be visible.")
parser.add_argument("--default-device", type=int, default=None, metavar="DEFAULT_DEVICE_ID", help="Set the id of the default device, all other devices will stay visible.")
cm_group = parser.add_mutually_exclusive_group()
cm_group.add_argument("--cuda-malloc", action="store_true", help="Enable cudaMallocAsync (enabled by default for torch 2.0 and up).")

10
comfy_extras/nodes_multigpu.py
View File

@ -45,6 +45,16 @@ class MultiGPUCFGSplitNode(io.ComfyNode):
class MultiGPUOptionsNode(io.ComfyNode):
"""
Select the relative speed of GPUs in the special case they have significantly different performance from one another.
NOTE (not registered yet, see MultiGPUExtension.get_node_list below):
The output GPUOptionsGroup is plumbed through create_multigpu_deepclones() and stored on
model.model_options['multigpu_options'] via GPUOptionsGroup.register(), but the cond
scheduler in comfy/samplers.py (calc_cond_batch_outer_multigpu) does NOT yet consult
relative_speed when distributing conds across devices; it uses a uniform conds_per_device
round-robin via next_available_device(). Before re-enabling this node, wire its
relative_speed into the scheduler (e.g. via comfy.multigpu.load_balance_devices(),
which already implements the proportional split) so the input actually affects work
distribution.
"""
@classmethod