From 92dd5703ecdb99aa4a4aee9817f28557907403a2 Mon Sep 17 00:00:00 2001 From: Tri Dao Date: Mon, 27 Nov 2023 16:23:39 -0800 Subject: [PATCH] Bump to v2.3.6 --- flash_attn/__init__.py | 2 +- training/Dockerfile | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/flash_attn/__init__.py b/flash_attn/__init__.py index 5e553da..a778d95 100644 --- a/flash_attn/__init__.py +++ b/flash_attn/__init__.py @@ -1,4 +1,4 @@ -__version__ = "2.3.5" +__version__ = "2.3.6" from flash_attn.flash_attn_interface import ( flash_attn_func, diff --git a/training/Dockerfile b/training/Dockerfile index 4747fde..47e01fb 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==2.3.5 +RUN pip install flash-attn==2.3.6 # Install CUDA extensions for fused dense, layer norm RUN git clone https://github.com/HazyResearch/flash-attention \ - && cd flash-attention && git checkout v2.3.4 \ + && cd flash-attention && git checkout v2.3.6 \ && cd csrc/layer_norm && pip install . && cd ../../ \ && cd csrc/fused_dense_lib && pip install . && cd ../../ \ && cd .. && rm -rf flash-attention