From 621e11b940ed586b50364bfd127e7256a88872bc Mon Sep 17 00:00:00 2001 From: kingbri Date: Tue, 5 Dec 2023 00:33:43 -0500 Subject: [PATCH] Update documentation Signed-off-by: kingbri --- README.md | 4 ++-- requirements.txt | 2 -- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index bd60728..eeb4f8e 100644 --- a/README.md +++ b/README.md @@ -18,9 +18,9 @@ To get started, make sure you have the following installed on your system: - Python 3.x (preferably 3.11) with pip -- CUDA 12.1 or 11.8 (or ROCm 5.6) +- CUDA 12.x (you can also use CUDA 11.8 or ROCm 5.6, but there will be more work required to install dependencies such as Flash Attention 2) -NOTE: For Flash Attention 2 to work on Windows, CUDA 12.1 **must** be installed! +NOTE: For Flash Attention 2 to work on Windows, CUDA 12.x **must** be installed! ## Installing diff --git a/requirements.txt b/requirements.txt index 15dd2c5..c73e597 100644 --- a/requirements.txt +++ b/requirements.txt @@ -6,8 +6,6 @@ uvicorn # Wheels -# Flash Attention 2. If the wheels don't work, comment these out, uncomment the old wheels, and run `pip install -r requirements.txt` - # Windows FA2 from https://github.com/jllllll/flash-attention/releases https://github.com/jllllll/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"