From 32163e7ce0f6c5dab07acea8a9bc36af71e0ac76 Mon Sep 17 00:00:00 2001 From: neavo Date: Sat, 1 Feb 2025 12:43:29 +0800 Subject: [PATCH] [readme] update flash attention installation instruction on win platform (#6788) * Update README_zh.md * Update README.md Former-commit-id: a417bcf8d9d70057d12f9152e4091c090133e025 --- README.md | 2 +- README_zh.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index c984cffe..efb4a55b 100644 --- a/README.md +++ b/README.md @@ -441,7 +441,7 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl #### Install Flash Attention-2 -To enable FlashAttention-2 on the Windows platform, you need to install the precompiled `flash-attn` library, which supports CUDA 12.1 to 12.2. Please download the corresponding version from [flash-attention](https://github.com/bdashore3/flash-attention/releases) based on your requirements. +To enable FlashAttention-2 on the Windows platform, please use the script from [flash-attention-windows-wheel](https://huggingface.co/lldacing/flash-attention-windows-wheel) to compile and install it by yourself. diff --git a/README_zh.md b/README_zh.md index 2157d11b..ac736767 100644 --- a/README_zh.md +++ b/README_zh.md @@ -443,7 +443,7 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl #### 安装 Flash Attention-2 -如果要在 Windows 平台上开启 FlashAttention-2，需要安装预编译的 `flash-attn` 库，支持 CUDA 12.1 到 12.2，请根据需求到 [flash-attention](https://github.com/bdashore3/flash-attention/releases) 下载对应版本安装。 +如果要在 Windows 平台上开启 FlashAttention-2，请使用 [flash-attention-windows-wheel](https://huggingface.co/lldacing/flash-attention-windows-wheel) 中的脚本自行编译与安装。