diff --git a/requirements-cu118.txt b/requirements-cu118.txt
index d804226..93df624 100644
--- a/requirements-cu118.txt
+++ b/requirements-cu118.txt
@@ -22,4 +22,4 @@ jinja2 >= 3.0.0
 colorlog
 
 # Linux FA2 from https://github.com/Dao-AILab/flash-attention/releases
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+cu118torch2.1cxx11abiFALSE-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/v2.4.1/flash_attn-2.4.1+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
diff --git a/requirements.txt b/requirements.txt
index a0bd32f..59e0cc6 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -23,10 +23,10 @@ colorlog
 
 # Flash attention v2
 
-# 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"
+# Windows FA2 from https://github.com/bdashore3/flash-attention/releases
+https://github.com/bdashore3/flash-attention/releases/download/v2.4.1/flash_attn-2.4.1+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/bdashore3/flash-attention/releases/download/v2.4.1/flash_attn-2.4.1+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 
 # Linux FA2 from https://github.com/Dao-AILab/flash-attention/releases
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.6/flash_attn-2.3.6+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/v2.3.6/flash_attn-2.3.6+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/v2.4.1/flash_attn-2.4.1+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/v2.4.1/flash_attn-2.4.1+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"