From fb124ab6e287302e1a4b48624031bbf4993f707b Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Tue, 21 Nov 2023 20:06:56 -0300 Subject: [PATCH] Bump to flash-attention 2.3.4 + switch to Github Actions wheels on Windows (#4700) --- one_click.py | 2 +- requirements.txt | 14 ++++++++------ requirements_noavx2.txt | 14 ++++++++------ 3 files changed, 17 insertions(+), 13 deletions(-) diff --git a/one_click.py b/one_click.py index 16433006..37aee8bd 100644 --- a/one_click.py +++ b/one_click.py @@ -303,7 +303,7 @@ def update_requirements(initial_installation=False): elif is_cuda118: textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements] if is_windows() and (is_cuda117 or is_cuda118): # No flash-attention on Windows for CUDA 11 - textgen_requirements = [req for req in textgen_requirements if 'bdashore3/flash-attention' not in req] + textgen_requirements = [req for req in textgen_requirements if 'jllllll/flash-attention' not in req] with open('temp_requirements.txt', 'w') as file: file.write('\n'.join(textgen_requirements)) diff --git a/requirements.txt b/requirements.txt index a9080412..d9f42e97 100644 --- a/requirements.txt +++ b/requirements.txt @@ -61,12 +61,14 @@ https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+ https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" -https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt index 32abd7d9..e1371e60 100644 --- a/requirements_noavx2.txt +++ b/requirements_noavx2.txt @@ -61,12 +61,14 @@ https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+ https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" -https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/bdashore3/flash-attention/releases/download/2.3.2-2/flash_attn-2.3.2+cu122-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" -https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" +https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"