Skip to content

feat: add KV caching support for Wan models #400

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

Open
Perseus14 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: add KV caching support for Wan models #400

Show file tree
Hide file tree
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
1 change: 1 addition & 0 deletions src/maxdiffusion/configs/base_wan_14b.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -355,6 +355,7 @@ use_cfg_cache: False
# Batch positive and negative prompts in text encoder to save compute.
use_batched_text_encoder: False

use_kv_cache: False
use_magcache: False
magcache_thresh: 0.12
magcache_K: 2
Expand Down
1 change: 1 addition & 0 deletions src/maxdiffusion/configs/base_wan_1_3b.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -301,6 +301,7 @@ flow_shift: 3.0

# Diffusion CFG cache (FasterCache-style, WAN 2.1 T2V only)
use_cfg_cache: False
use_kv_cache: False

# Batch positive and negative prompts in text encoder to save compute.
use_batched_text_encoder: False
Expand Down
2 changes: 1 addition & 1 deletion src/maxdiffusion/configs/base_wan_27b.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,7 +331,7 @@ use_cfg_cache: False
# Batch positive and negative prompts in text encoder to save compute.
use_batched_text_encoder: False


use_kv_cache: False
# SenCache: Sensitivity-Aware Caching (arXiv:2602.24208) — skip forward pass
# when predicted output change (based on accumulated latent/timestep drift) is small
use_sen_cache: False
Expand Down
2 changes: 1 addition & 1 deletion src/maxdiffusion/configs/base_wan_i2v_14b.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -318,7 +318,7 @@ use_cfg_cache: False
# Batch positive and negative prompts in text encoder to save compute.
use_batched_text_encoder: False


use_kv_cache: False
# SenCache: Sensitivity-Aware Caching (arXiv:2602.24208)
use_sen_cache: False
use_magcache: False
Expand Down
2 changes: 1 addition & 1 deletion src/maxdiffusion/configs/base_wan_i2v_27b.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,7 +330,7 @@ use_cfg_cache: False
# Batch positive and negative prompts in text encoder to save compute.
use_batched_text_encoder: False


use_kv_cache: False
# SenCache: Sensitivity-Aware Caching (arXiv:2602.24208)
use_sen_cache: False

Expand Down
Loading
Loading