From 4f87b232c27052c4087747de79e264725f7258bb Mon Sep 17 00:00:00 2001 From: leejet Date: Wed, 28 Aug 2024 00:24:53 +0800 Subject: [PATCH] docs: add Vulkan build command --- README.md | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 95fd5e6..c66b10a 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ Inference of Stable Diffusion and Flux in pure C/C++ - 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. - 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 - No need to convert to `.ggml` or `.gguf` anymore! - Flash Attention for memory usage optimization (only cpu for now) @@ -142,6 +142,15 @@ cmake .. -DSD_METAL=ON 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 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).