add runpod envs to .bashrc, fix bnb env (axolotl-ai-cloud#316)

* hopper support for base dockerfile, add runpod envs to .bashrc

* set BNB_CUDA_VERSION env for latest bnb

* don't support hopper yet w 118

Author: winglian

.github/workflows/main.yml

@@ -69,22 +69,22 @@ jobs:
     strategy:
       matrix:
         include:
-          - cuda: cu118
+          - cuda: 118
             cuda_version: 11.8.0
             python_version: "3.9"
             pytorch: 2.0.1
             axolotl_extras:
-          - cuda: cu118
+          - cuda: 118
             cuda_version: 11.8.0
             python_version: "3.10"
             pytorch: 2.0.1
             axolotl_extras:
-          - cuda: cu118
+          - cuda: 118
             cuda_version: 11.8.0
             python_version: "3.9"
             pytorch: 2.0.1
             axolotl_extras: gptq
-          - cuda: cu117
+          - cuda: 117
             cuda_version: 11.7.1
             python_version: "3.9"
             pytorch: 1.13.1
@@ -110,8 +110,9 @@ jobs:
         with:
           context: .
           build-args: |
-            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            CUDA=${{ matrix.cuda }}
           file: ./docker/Dockerfile-runpod
           push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
           labels: ${{ steps.metadata.outputs.labels }}

docker/Dockerfile

@@ -3,6 +3,8 @@ FROM winglian/axolotl-base:$BASE_TAG
 
 ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
 ARG AXOLOTL_EXTRAS=""
+ARG CUDA="118"
+ENV BNB_CUDA_VERSION=$CUDA
 
 RUN apt-get update && \
     apt-get install -y vim curl

scripts/runpod-entrypoint.sh

@@ -1,10 +1,21 @@
 #!/bin/bash
 
-echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
-chmod 700 -R ~/.ssh
+# Export specific ENV variables to /etc/rp_environment
+echo "Exporting environment variables..."
+printenv | grep -E '^RUNPOD_|^PATH=|^_=' | sed 's/^\(.*\)=\(.*\)$/export \1="\2"/' >> /etc/rp_environment
+echo 'source /etc/rp_environment' >> ~/.bashrc
 
-# Start the SSH service in the background
-service ssh start
+if [[ $PUBLIC_KEY ]]
+then
+    mkdir -p ~/.ssh
+    chmod 700 ~/.ssh
+    echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
+    chmod 700 -R ~/.ssh
+    # Start the SSH service in the background
+    service ssh start
+else
+    echo "No PUBLIC_KEY ENV variable provided, not starting openSSH daemon"
+fi
 
 # Execute the passed arguments (CMD)
 exec "$@"