alphard/stable-diffusion.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: add Vulkan build command

Browse Source
This commit is contained in:
leejet 2024-08-28 00:24:53 +08:00
parent e71ddcedad
commit 4f87b232c2
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@ -21,7 +21,7 @@ Inference of Stable Diffusion and Flux in pure C/C++
- Accelerated memory-efficient CPU inference - Accelerated memory-efficient CPU inference
- Only requires ~2.3GB when using txt2img with fp16 precision to generate a 512x512 image, enabling Flash Attention just requires ~1.8GB. - Only requires ~2.3GB when using txt2img with fp16 precision to generate a 512x512 image, enabling Flash Attention just requires ~1.8GB.
- AVX, AVX2 and AVX512 support for x86 architectures - AVX, AVX2 and AVX512 support for x86 architectures
- Full CUDA, Metal and SYCL backend for GPU acceleration. - Full CUDA, Metal, Vulkan and SYCL backend for GPU acceleration.
- Can load ckpt, safetensors and diffusers models/checkpoints. Standalone VAEs models - Can load ckpt, safetensors and diffusers models/checkpoints. Standalone VAEs models
- No need to convert to `.ggml` or `.gguf` anymore! - No need to convert to `.ggml` or `.gguf` anymore!
- Flash Attention for memory usage optimization (only cpu for now) - Flash Attention for memory usage optimization (only cpu for now)
@ -142,6 +142,15 @@ cmake .. -DSD_METAL=ON
cmake --build . --config Release cmake --build . --config Release
``` ```
##### Using Vulkan
Install Vulkan SDK from https://www.lunarg.com/vulkan-sdk/.
```
cmake .. -DSD_VULKAN=ON
cmake --build . --config Release
```
##### Using SYCL ##### Using SYCL
Using SYCL makes the computation run on the Intel GPU. Please make sure you have installed the related driver and [Intel® oneAPI Base toolkit](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit.html) before start. More details and steps can refer to [llama.cpp SYCL backend](https://github.com/ggerganov/llama.cpp/blob/master/docs/backend/SYCL.md#linux). Using SYCL makes the computation run on the Intel GPU. Please make sure you have installed the related driver and [Intel® oneAPI Base toolkit](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit.html) before start. More details and steps can refer to [llama.cpp SYCL backend](https://github.com/ggerganov/llama.cpp/blob/master/docs/backend/SYCL.md#linux).