Skip to content

improved flux attention qkv unpacking - #1306

Merged
leejet merged 2 commits into
leejet:masterfrom
bssrdf:improve-flux-attn-qkv
Mar 3, 2026
Merged

improved flux attention qkv unpacking#1306
leejet merged 2 commits into
leejet:masterfrom
bssrdf:improve-flux-attn-qkv

Conversation

@bssrdf

@bssrdf bssrdf commented Mar 1, 2026

Copy link
Copy Markdown
Contributor

This PR improves performance a bit for flux models by getting rid of some ggml_cont ops.

RTX 4090

FLUX.2 Klein 4B (CFG 1, 4 steps, bf16) master This PR
512x512 7.8it/s 8.2it/s
1024x1024 2.5it/s 2.57it/s

@bssrdf bssrdf changed the title improved flux attention speed by removing cont op for qkv improved flux attention qkv unpacking by removing cont op Mar 1, 2026
@bssrdf bssrdf changed the title improved flux attention qkv unpacking by removing cont op improved flux attention qkv unpacking Mar 1, 2026
@leejet
leejet merged commit d41f5ff into leejet:master Mar 3, 2026
14 checks passed
@leejet

leejet commented Mar 3, 2026

Copy link
Copy Markdown
Owner

Thank you for your contribution.

@bssrdf
bssrdf deleted the improve-flux-attn-qkv branch March 6, 2026 21:30
gianni-cor pushed a commit to gianni-cor/stable-diffusion.cpp that referenced this pull request May 18, 2026
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