use new script to run docs, and run for CPU and CUDA (#756)

* use new script to run docs, and run for CPU and CUDA

* typo

Author: mikekgfb

.ci/scripts/run-docs

@@ -0,0 +1,42 @@
+# /bin/bash -x
+
+if [ "X$1" == "X" ]; then
+  echo "Must specify document to run"
+  exit 1
+fi
+
+if [ "$1" == "readme" ]; then
+        echo "::group::Create script to run README"
+        python3 scripts/updown.py --create-sections --file README.md --replace 'llama3:stories15M,-l 3:-l 2,meta-llama/Meta-Llama-3-8B-Instruct:stories15M' --suppress huggingface-cli,HF_TOKEN > ./run-readme.sh
+        # for good measure, if something happened to updown processor,
+        # and it did not error out, fail with an exit 1
+        echo "exit 1" >> ./run-readme.sh
+        echo "::endgroup::"
+
+        echo "::group::Run README"
+        echo "*******************************************"
+        cat ./run-readme.sh
+        echo "*******************************************"
+        bash -x ./run-readme.sh
+        echo "::endgroup::"
+
+        exit 0
+fi
+
+if [ "$1" == "quantization" ]; then
+        echo "::group::Create script to run quantization"
+        python3 scripts/updown.py --create-sections --file docs/quantization.md --replace llama3:stories15M --suppress huggingface-cli,HF_TOKEN > ./run-quantization.sh
+        # for good measure, if something happened to updown processor,
+        # and it did not error out, fail with an exit 1
+        echo "exit 1" >> ./run-quantization.sh
+        echo "::endgroup::"
+
+        echo "::group::Run quantization"
+        echo "*******************************************"
+        cat ./run-quantization.sh
+        echo "*******************************************"
+        bash -x ./run-quantization.sh
+        echo "::endgroup::"
+
+        exit 0
+fi

.github/workflows/run-readme-pr.yml

@@ -27,20 +27,33 @@ jobs:
         export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH
         echo "::endgroup::"
 
-        echo "::group::Create script to run README"
-        python3 scripts/updown.py --create-sections --file README.md --replace 'llama3:stories15M,-l 3:-l 2,meta-llama/Meta-Llama-3-8B-Instruct:stories15M' --suppress huggingface-cli,HF_TOKEN > ./run-readme.sh
-        # for good measure, if something happened to updown processor,
-        # and it did not error out, fail with an exit 1
-        echo "exit 1" >> ./run-readme.sh
-        echo "::endgroup::"
+        .ci/scripts/run-docs readme
 
-        echo "::group::Run README"
-        echo "*******************************************"
-        cat ./run-readme.sh
+        echo "::group::Completion"
+        echo "tests complete"
         echo "*******************************************"
-        bash -x ./run-readme.sh
         echo "::endgroup::"
 
+  test-readme-cpu:
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    with:
+      runner: linux.g5.4xlarge.nvidia.gpu
+      secrets-env: "HF_TOKEN_PERIODIC"
+      gpu-arch-type: cuda
+      gpu-arch-version: "12.1"
+      timeout: 60
+      script: |
+        echo "::group::Print machine info"
+        uname -a
+        echo "::endgroup::"
+
+        echo "::group::Install newer objcopy that supports --set-section-alignment"
+        yum install -y  devtoolset-10-binutils
+        export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH
+        echo "::endgroup::"
+
+        TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs readme
+
         echo "::group::Completion"
         echo "tests complete"
         echo "*******************************************"
@@ -63,20 +76,32 @@ jobs:
         export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH
         echo "::endgroup::"
 
-        echo "::group::Create script to run quantization"
-        python3 scripts/updown.py --create-sections --file docs/quantization.md --replace llama3:stories15M --suppress huggingface-cli,HF_TOKEN > ./run-quantization.sh
-        # for good measure, if something happened to updown processor,
-        # and it did not error out, fail with an exit 1
-        echo "exit 1" >> ./run-quantization.sh
-        echo "::endgroup::"
+        .ci/scripts/run-docs quantization
 
-        echo "::group::Run quantization"
-        echo "*******************************************"
-        cat ./run-quantization.sh
+        echo "::group::Completion"
+        echo "tests complete"
         echo "*******************************************"
-        bash -x ./run-quantization.sh
         echo "::endgroup::"
 
+  test-quantization-cpu:
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    with:
+      runner: linux.g5.4xlarge.nvidia.gpu
+      gpu-arch-type: cuda
+      gpu-arch-version: "12.1"
+      timeout: 60
+      script: |
+        echo "::group::Print machine info"
+        uname -a
+        echo "::endgroup::"
+
+        echo "::group::Install newer objcopy that supports --set-section-alignment"
+        yum install -y  devtoolset-10-binutils
+        export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH
+        echo "::endgroup::"
+
+        TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs quantization
+
   test-gguf-any:
     uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     secrets: inherit