Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

2017 Google Pixelbook (intel i7, intel iris 615?) #121

RogerDass started this conversation in Benchmark
Discussion options

Hello!

Thanks for making this amazing project!

So i'm running this with realistic vision v1.5 checkpoint. I'm getting ~75 s/it with OpenBLAS enabled.
Any idea how to speed that up significantly?

With ComfyUI on the same machine in CPU mode, I'm getting ~30 s/it and it takes 10 min to generate 512x512 image with 20 steps.

What's causing such a large performance difference?

Do you know if there's a way to get some basic OpenGL 3 acceleration for some of the tensor ops?

You must be logged in to vote

Replies: 5 comments

Comment options

My observation is that ggml does not achieve maximum convolution optimization, my solution is to use turbo model or configure quantization, such as q8_0

You must be logged in to vote
0 replies
Comment options

use lcm lora sdv1.5 with 4 steps and taesd it be much faster

You must be logged in to vote
0 replies
Comment options

~75 it/s

pretty sure you meant s/it

You must be logged in to vote
0 replies
Comment options

Yeah s/it...

Please keep in mind that ComfyUI is using f32 and not any lower quantization with 20 steps and is more than 2X faster.

Anyone know what tensorvision-cpu is doing that's so much faster than gglm?

You must be logged in to vote
0 replies
Comment options

@RogerDass It's just that PyTorch implements more optimized convolution algorithms that are too complex to implement in ggml. That's why PyTorch is quite heavy; instead of reinventing the wheel, they reuse existing code to avoid unnecessary complications.

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

AltStyle によって変換されたページ (->オリジナル) /