Skip to content

Conversation

@rmatif
Copy link
Contributor

@rmatif rmatif commented Nov 4, 2025

This PR adds support for Easycache, a variant of TeaCache that achieves significant speedup

Currently tested only with CUDA and on Flux/Qwen

Command usage:

--easycache threshold,start_percent,end_percent

Examples:

Without Easycache --easycache 0.2,0.15,0.95 Speedup
output2 output3 x1.85
noeasycache easycache x1.85

@Green-Sky
Copy link
Contributor

Green-Sky commented Nov 6, 2025

Ran it with a SPARK (preview) Chroma finetune

thresh img real speedup
0 ec_chroma spark_noec baseline
0.025 ec_chroma spark_0 025 1.12x
0.1 ec_chroma spark_0 1 1.31x
0.2 ec_chroma spark_0 2 1.4x

I noticed the estimated speedup is off. It is off exactly by 2x, so I guess cfg is not handled properly yet.

eg. 40steps with cfg are actually 80 steps

40/(40-8) -> 1.25 (estimated 1.25)
80/(80-8) -> 1.11 (measured 1.12)

I included 0.025, because that is what the original used for wan.

Anyway Good stuff, I take the 11% speedup.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants