lllyasviel / lllyasviel/FramePack

Is SageAttention, etc. actually implemented?

Open
#7 11 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
17.3k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

I'm getting about 6.5 seconds per frame on a 4090, so I was thinking the 2.5 seconds might be with sageattention, etc. I installed it, it said "Sage Attn is installed!", but the generation speed didn't change.

~~So I checked the code and it looks like it gets imported but never used. Maybe I missed something?~~

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file or test is named in the issue. Start by tracing the SageAttention import through the generation path and compare timing with and without it. Done means confirming whether the installed attention implementation is actually used and explaining any unchanged generation speed.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.