Skip to content

fix(offload): keep the working set resident under balanced when it fits the budget #4968

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
QualiaRain wants to merge 1 commit into
base: dev
Choose a base branch
from
+5 −1
Draft

fix(offload): keep the working set resident under balanced when it fits the budget #4968

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion modules/sd_offload.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -450,7 +450,11 @@ def do_move(module):
op = f'{op}:always'
module = do_move(module)
used_gpu -= module_size
elif perc_gpu > shared.opts.diffusers_offload_min_gpu_memory:
# only offload under genuine memory pressure: if the whole working set already fits within the
# GPU budget (diffusers_offload_max_gpu_memory) then offloading here just forces a costly
# re-onload on the module's next forward -- e.g. the UNet evicted to run the text encoder / VAE
# then re-dispatched every generation (~2x slowdown on cards with spare VRAM).
elif perc_gpu > shared.opts.diffusers_offload_min_gpu_memory and offload_hook_instance.model_size() > offload_hook_instance.gpu / (1024 ** 3):
op = f'{op}:mem'
module = do_move(module)
used_gpu -= module_size
Expand Down
Loading