diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index 4f57d77..d679608 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -64,11 +64,11 @@ jobs:
               python-version: '3.7'
             # Pytorch <= 2.0 only supports CUDA <= 11.8
             - torch-version: '1.12.1'
-              cuda-version: '12.2.0'
+              cuda-version: '12.2.2'
             - torch-version: '1.13.1'
-              cuda-version: '12.2.0'
+              cuda-version: '12.2.2'
             - torch-version: '2.0.1'
-              cuda-version: '12.2.0'
+              cuda-version: '12.2.2'
 
     steps:
       - name: Checkout
diff --git a/flash_attn/__init__.py b/flash_attn/__init__.py
index 94b1dd2..eda72f3 100644
--- a/flash_attn/__init__.py
+++ b/flash_attn/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "2.4.3"
+__version__ = "2.4.3.post1"
 
 from flash_attn.flash_attn_interface import (
     flash_attn_func,
diff --git a/training/Dockerfile b/training/Dockerfile
index 8729647..9d49c2f 100644
--- a/training/Dockerfile
+++ b/training/Dockerfile
@@ -85,7 +85,7 @@ RUN pip install transformers==4.25.1 datasets==2.8.0 pytorch-lightning==1.8.6 tr
 RUN pip install git+https://github.com/mlcommons/logging.git@2.1.0
 
 # Install FlashAttention
-RUN pip install flash-attn==2.4.3
+RUN pip install flash-attn==2.4.3.post1
 
 # Install CUDA extensions for fused dense
 RUN pip install git+https://github.com/HazyResearch/flash-attention@v2.4.2#subdirectory=csrc/fused_dense_lib