From 3a91ca2dd191716be9e9f3f20627c1e1a80d13f1 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Sun, 17 Aug 2025 13:57:23 -0700 Subject: [PATCH] Update flash attention --- requirements/full/requirements.txt | 4 ++-- requirements/full/requirements_noavx2.txt | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt index eeee9ff3..d57a457c 100644 --- a/requirements/full/requirements.txt +++ b/requirements/full/requirements.txt @@ -41,5 +41,5 @@ https://github.com/turboderp-org/exllamav3/releases/download/v0.0.6/exllamav3-0. https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64" -https://github.com/kingbri1/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/kingbri1/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.7cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt index d08f23ca..b073a3a9 100644 --- a/requirements/full/requirements_noavx2.txt +++ b/requirements/full/requirements_noavx2.txt @@ -41,5 +41,5 @@ https://github.com/turboderp-org/exllamav3/releases/download/v0.0.6/exllamav3-0. https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64" -https://github.com/kingbri1/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" -https://github.com/kingbri1/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" +https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.7.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" +https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.7cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"