[example] diffusion install from docker (#2239)

* [builder] builder for scaled_upper_triang_masked_softmax

* add missing files

* fix a bug

* polish code

* [example] diffusion install from docker

examples/images/diffusion/docker/Dockerfile

@@ -0,0 +1,41 @@
+FROM hpcaitech/pytorch-cuda:1.12.0-11.3.0
+
+# install torch
+# RUN conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
+RUN apt-get update
+RUN apt-get install ffmpeg libsm6 libxext6  -y
+
+# install apex
+RUN git clone https://github.com/NVIDIA/apex && \
+    cd apex && \
+    pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" --global-option="--fast_layer_norm" ./
+
+# install colossalai
+# RUN git clone https://github.com/hpcaitech/ColossalAI.git \
+#     && cd ./ColossalAI \
+#     && pip install -v --no-cache-dir .
+
+RUN pip install colossalai==0.1.12+torch1.12cu11.3 -f https://release.colossalai.org
+
+
+# install our lightning, it will be merged to Lightning official repo.
+RUN git clone https://github.com/1SAA/lightning.git && \
+    cd lightning && \
+    git checkout strategy/colossalai && \
+    export PACKAGE_NAME=pytorch && \
+    pip install --no-cache-dir .
+
+# install titans
+RUN pip install --no-cache-dir titans
+
+RUN git clone https://github.com/hpcaitech/ColossalAI.git  && \
+    cd ./ColossalAI/examples/images/diffusion && \
+    pip install -r requirements.txt && \
+    pip install --no-cache-dir transformers==4.19.2 diffusers invisible-watermark
+
+# install tensornvme
+# RUN conda install cmake && \
+#     git clone https://github.com/hpcaitech/TensorNVMe.git && \
+#     cd TensorNVMe && \
+#     pip install -r requirements.txt && \
+#     pip install -v --no-cache-dir .