diff --git a/README.md b/README.md
index 88ba4ed..79d3345 100644
--- a/README.md
+++ b/README.md
@@ -101,7 +101,7 @@ Return:
 flash_attn_func(q, k, v, dropout_p=0.0, softmax_scale=None, causal=False):
 """dropout_p should be set to 0.0 during evaluation
 Supports multi-query and grouped-query attention (MQA/GQA) by passing in KV with fewer heads
-than Q. Note that the number of heads in KV must be divisible by the number of heads in Q.
+than Q. Note that the number of heads in Q must be divisible by the number of heads in KV.
 For example, if Q has 6 heads and K, V have 2 heads, head 0, 1, 2 of Q will attention to head
 0 of K, V, and head 3, 4, 5 of Q will attention to head 1 of K, V.
 
@@ -131,7 +131,7 @@ These functions have been renamed:
 If the inputs have the same sequence lengths in the same batch, it is simpler
 and faster to use these functions:
 ```python
-flash_attn_qkvpacked_func(qkv, dropout_p, softmax_scale=None, causal=False)
+flash_attn_qkvpacked_func(qkv, dropout_p=0.0, softmax_scale=None, causal=False)
 ```
 ```python
 flash_attn_func(q, k, v, dropout_p=0.0, softmax_scale=None, causal=False)
diff --git a/flash_attn/__init__.py b/flash_attn/__init__.py
index f9a3f96..0572f72 100644
--- a/flash_attn/__init__.py
+++ b/flash_attn/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "2.0.3"
+__version__ = "2.0.4"
 
 from flash_attn.flash_attn_interface import flash_attn_func
 from flash_attn.flash_attn_interface import flash_attn_kvpacked_func
diff --git a/training/Dockerfile b/training/Dockerfile
index 94a5768..3bc477a 100644
--- a/training/Dockerfile
+++ b/training/Dockerfile
@@ -85,11 +85,11 @@ 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==2.0.3
+RUN pip install flash-attn==2.0.4
 
 # Install CUDA extensions for cross-entropy, fused dense, layer norm
 RUN git clone https://github.com/HazyResearch/flash-attention \
-    && cd flash-attention && git checkout v2.0.3 \
+    && cd flash-attention && git checkout v2.0.4 \
     && cd csrc/fused_softmax && pip install . && cd ../../ \
     && cd csrc/rotary && pip install . && cd ../../ \
     && cd csrc/xentropy && pip install . && cd ../../ \