update ggml and adjust for new type

[Green-Sky]

No description provided.

[wbruna]

Related: #760 .

[Green-Sky]

@wbruna right, you where first. 😄

[rmatif]

This will solve this issue also #757

[wbruna]

@wbruna right, you where first. 😄

Oh, my PR doesn't actually bump SD_TYPE_COUNT, it just makes it easier to upgrade/downgrade ggml without dealing with that :-)

[Green-Sky]

CUDA fp16 sd1 performance degraded ggml-org/ggml@323951f...5fdc78f
diffusion from ~1.6it/s to ~1.4it/s
vae from ~0.7s to ~0.8s
(diffusion fa on/off sees similar degradation)

Nevermind, I think my gpu just got hot. 😅

[wbruna]

CUDA fp16 sd1 performance degraded ggml-org/ggml@323951f...5fdc78f
diffusion from ~1.6it/s to ~1.4it/s
vae from ~0.7s to ~0.8s
(diffusion fa on/off sees similar degradation)

Nevermind, I think my gpu just got hot. 😅

Well, this did help me notice FA on the wan branch makes full-black images for SD1.5 🙁

I also noticed a consistent slowdown for the Conv2D VAE, but it's very small (~3%).

[wbruna]

Well, this did help me notice FA on the wan branch makes full-black images for SD1.5 🙁

Huh, except it's working on master now - and giving a nice 20% speed boost. Chroma is now working with FA, too.

(btw, this PR was superseded by #778 )