Dcoker images runtime -> devel (#16141)

* Runtime -> Devel

* Torch before DeepSpeed

docker/transformers-all-latest-gpu/Dockerfile

-FROM nvidia/cuda:11.2.2-cudnn8-runtime-ubuntu20.04
+FROM nvidia/cuda:11.2.2-cudnn8-devel-ubuntu20.04
 LABEL maintainer="Hugging Face"
 
 ARG DEBIAN_FRONTEND=noninteractive

docker/transformers-doc-builder/Dockerfile

@@ -4,9 +4,12 @@ LABEL maintainer="Hugging Face"
 RUN apt update
 RUN git clone https://github.com/huggingface/transformers
 
-RUN python3 -m pip install --no-cache-dir --upgrade pip && python3 -m pip install --no-cache-dir git+https://github.com/huggingface/doc-builder ./transformers[dev,deepspeed]
+RUN python3 -m pip install --no-cache-dir --upgrade pip && python3 -m pip install --no-cache-dir git+https://github.com/huggingface/doc-builder ./transformers[dev]
 RUN apt-get -y update && apt-get install -y libsndfile1-dev && apt install -y tesseract-ocr
 
+# Torch needs to be installed before deepspeed
+RUN python3 -m pip install --no-cache-dir ./transformers[deepspeed]
+
 RUN python3 -m pip install --no-cache-dir torch-scatter -f https://data.pyg.org/whl/torch-$(python -c "from torch import version; print(version.__version__.split('+')[0])")+cpu.html
 RUN python3 -m pip install --no-cache-dir torchvision git+https://github.com/facebookresearch/detectron2.git pytesseract https://github.com/kpu/kenlm/archive/master.zip
 RUN python3 -m pip install --no-cache-dir pytorch-quantization --extra-index-url https://pypi.ngc.nvidia.com

docker/transformers-pytorch-gpu/Dockerfile

-FROM nvidia/cuda:11.2.2-cudnn8-runtime-ubuntu20.04
+FROM nvidia/cuda:11.2.2-cudnn8-devel-ubuntu20.04
 LABEL maintainer="Hugging Face"
 
 ARG DEBIAN_FRONTEND=noninteractive

docker/transformers-tensorflow-gpu/Dockerfile

-FROM nvidia/cuda:11.2.2-cudnn8-runtime-ubuntu20.04
+FROM nvidia/cuda:11.2.2-cudnn8-devel-ubuntu20.04
 LABEL maintainer="Hugging Face"
 
 ARG DEBIAN_FRONTEND=noninteractive