Comments (6)
Can you give a detailed log?
from stable-diffusion.cpp.
I found RTX4090 and GTX1660S is the same speed of sampling,and they are costing CPU a lot performance.
Then I search the code of the conv2d, and found that conv2d is only for CPU impl.
https://github.com/FSSRepo/ggml/blob/70474c6890c015b53dc10a2300ae35246cc73589/src/ggml-cuda.cu
There is no GPU impl about conv2d.
https://github.com/FSSRepo/ggml/blob/70474c6890c015b53dc10a2300ae35246cc73589/src/ggml.c
Here is the CPU conv2d.
from stable-diffusion.cpp.
Let me check again with latest version tomorrow.
from stable-diffusion.cpp.
Consider add clblast conv func to support OpenCL?
from stable-diffusion.cpp.
The conv_2d operation is divided into two steps: im2col and mul_mat. Hence, you won't find the implementation related to conv2d directly in ggml-cuda.cu.
from stable-diffusion.cpp.
forgot add -DSD_CUBLAS. GGML_CUBLAS is no use.
from stable-diffusion.cpp.
Related Issues (20)
- Problems with function "ggml_quantize_chunk" on M1 in ggml.c HOT 1
- Enhance:free_params_immediately can be infer again HOT 4
- Support for splitting buffers M1/M2/M3
- Enhance: can set options without load model again. HOT 2
- support for bigger seeds and token
- unsupported dtype 'F64' HOT 10
- lora can not free memory HOT 1
- IP Adapter Direct ML Errors Controlnet 1.1.431 and UP HOT 1
- "CUDA error" when set resolution higher than 1280 x 1280 HOT 5
- Support Segmind Stable Diffusion 1B HOT 2
- rocBLAS error: {...} No such file or directory for GPU arch : gfx1031 HOT 6
- In lora.hpp miss ggml_free(ctx0);
- Will Controlnet be supported in the future? HOT 2
- VAE-Tiling seems to be always enabled in the C-API of 36ec16a HOT 1
- How do specify the upscale size? HOT 2
- to do list remove the winograd conv 2d
- Getting always black image using XL models HOT 2
- Is there a way to use controlnet inpaint?
- Using (UTF-8) accented characters give a segfault
- Are SDXL Controlnet models supported? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stable-diffusion.cpp.