[SDPA] Make sure attn mask creation is always done on CPU (#28400)

* [SDPA] Make sure attn mask creation is always done on CPU

* Update docker to 2.1.1

* revert test change

docker/transformers-all-latest-gpu/Dockerfile

@@ -9,9 +9,9 @@ SHELL ["sh", "-lc"]
 # The following `ARG` are mainly used to specify the versions explicitly & directly in this docker file, and not meant
 # to be used as arguments for docker build (so far).
 
-ARG PYTORCH='2.1.0'
+ARG PYTORCH='2.1.1'
 # (not always a valid torch version)
-ARG INTEL_TORCH_EXT='2.1.0'
+ARG INTEL_TORCH_EXT='2.1.1'
 # Example: `cu102`, `cu113`, etc.
 ARG CUDA='cu118'
 

docker/transformers-pytorch-gpu/Dockerfile

@@ -11,7 +11,7 @@ ARG REF=main
 RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
 
 # If set to nothing, will install the latest version
-ARG PYTORCH='2.1.0'
+ARG PYTORCH='2.1.1'
 ARG TORCH_VISION=''
 ARG TORCH_AUDIO=''
 # Example: `cu102`, `cu113`, etc.