build: add tool to compute model memory size

Signed-off-by: Jeff MAURY <[email protected]>

.github/workflows/compute-model-sizes.yml

@@ -0,0 +1,21 @@
+# This is a basic workflow that is manually triggered
+
+name: Compute model sizes
+
+# Controls when the action will run. Workflow runs when manually triggered using the UI
+# or API.
+on:
+  workflow_dispatch:
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  # This workflow contains a single job called "greet"
+  compute:
+    # The type of runner that the job will run on
+    runs-on: ubuntu-latest
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+    - uses: actions/checkout@v4
+    # Runs a single command using the runners shell
+    - name: Compute model size
+      run: ./tools/compute-model-sizes.sh

tools/compute-model-sizes.sh

@@ -0,0 +1,7 @@
+echo 'FROM registry.access.redhat.com/ubi9-minimal:9.3' >Containerfile
+echo 'RUN microdnf install -y git make g++' >>Containerfile
+echo 'RUN git clone https://github.com/ggerganov/llama.cpp' >>Containerfile
+echo 'RUN cd llama.cpp && make simple' >>Containerfile
+echo 'RUN pwd' >>Containerfile
+podman build . -t get-model-size
+cat packages/backend/src/assets/ai.json | jq -r .models[].url | while read i; do echo $i; curl -s -L -o model $i; podman run --rm -t --security-opt 'label=disable' -v `pwd`/model:/model get-model-size llama.cpp/simple /model a | grep 'model size'; rm model; done