Name a CPU-only Dockerfile since the NVidia turned out to be complica…

…ted to make actually work due to NVidia's own shenanigans.

It seems to be difficult to get OpenCL powered by NVidia inside a
container. My Linux did not have the necessary packages in repositories
(Fedora) to expose NVidia GPUs inside docker.

.docker/nvidia.dockerfile → .docker/cpu.dockerfile

@@ -8,23 +8,13 @@ RUN apt install -y curl \
     tar \
     curl \
     xz-utils \
-    ocl-icd-libopencl1 \
-    opencl-headers \
-    clinfo \
     build-essential \
     gcc
 
-RUN mkdir -p /etc/OpenCL/vendors && \
-    echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
-ENV NVIDIA_VISIBLE_DEVICES all
-ENV NVIDIA_DRIVER_CAPABILITIES compute,utility
-
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs > /rustup.sh
 RUN chmod +x /rustup.sh
 RUN /rustup.sh -y
 
-RUN apt install -y opencl-dev
-
 RUN bash -c 'export LD_LIBRARY_PATH=/usr/lib:/lib:/usr/lib64:/lib64; export PATH="$PATH:$HOME/.cargo/bin";rustup default nightly'
 
 COPY . /opt/rllama

.dockerignore

@@ -0,0 +1 @@
+target

README.md

@@ -54,6 +54,27 @@ RUSTFLAGS="-C target-feature=+sse2,+avx,+fma,+avx2" cargo install rllama
 There is a `.cargo/config.toml` inside this repository that will enable these
 features if you install manually from this Git repository instead.
 
+## Install (Docker path)
+
+There is a Dockerfile you can use if you'd rather just get started quickly and
+you are familiar with `docker`. You still need to download the models yourself.
+
+```
+docker build -f ./.docker/cpu.dockerfile -t rllama .
+```
+
+```
+docker run -v /models/LLaMA:/models:z -it rllama \
+    rllama --model-path /models/7B \
+           --param-path /models/7B/params.json \
+           --tokenizer-path /models/tokenizer.model \
+           --prompt "hi I like cheese"
+```
+
+Replace `/models/LLaMA` with the directory you've downloaded your models to.
+The `:z` in `-v` flag may or may not be needed depending on your distribution
+(I needed it on Fedora Linux)
+
 ## LLaMA weights
 
 Refer to https://github.com/facebookresearch/llama/ As of now, you need to be