comfyanonymous/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-19 06:30:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Made multigpu deepclone load model from disk to avoid needing to deepclone actual model object, fixed issues with merge, turn off cuda backend as it causes device mismatch issue with rope (and potentially other ops), will investigate

Browse Source
This commit is contained in:
Jedrzej Kosinski
2026-02-17 04:55:00 -08:00
parent df2fd4c869
commit f4b99bc623
4 changed files with 15 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/quant_ops.py
View File

@@ -20,7 +20,7 @@ try:
if cuda_version < (13,):
ck.registry.disable("cuda")
logging.warning("WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.")
ck.registry.disable("cuda") # multigpu will not work rn with comfy-kitchen on cuda backend
ck.registry.disable("triton")
for k, v in ck.list_backends().items():
logging.info(f"Found comfy_kitchen backend {k}: {v}")