Parametrise llama-server version in release pipeline

Signed-off-by: Piotr Stankiewicz <[email protected]>

Author: Piotr Stankiewicz

.github/workflows/release.yml

@@ -14,6 +14,11 @@ on:
         required: false
         type: string
         default: "test"
+      llamaServerVersion:
+        description: 'llama-server version'
+        required: false
+        type: string
+        default: "latest"
 
 jobs:
   test:
@@ -75,7 +80,7 @@ jobs:
           file: Dockerfile
           platforms: linux/amd64, linux/arm64
           build-args: |
-            "LLAMA_SERVER_VERSION=latest"
+            "LLAMA_SERVER_VERSION=${{ inputs.llamaServerVersion }}"
           push: true
           sbom: true
           provenance: mode=max
@@ -87,7 +92,7 @@ jobs:
           file: Dockerfile
           platforms: linux/amd64, linux/arm64
           build-args: |
-            "LLAMA_SERVER_VERSION=latest"
+            "LLAMA_SERVER_VERSION=${{ inputs.llamaServerVersion }}"
             "LLAMA_SERVER_VARIANT=cuda"
             "BASE_IMAGE=nvidia/cuda:12.9.0-runtime-ubuntu24.04"
           push: true