Add healthchecks to llama-server containers (#8081)

* added healthcheck

* added healthcheck

* added healthcheck

* added healthcheck

* added healthcheck

* moved curl to base

* moved curl to base

diff --git a/.devops/llama-server-cuda.Dockerfile b/.devops/llama-server-cuda.Dockerfile
index 0010ffd4c5465e5ecea68505883f03bbbcaa95b0..7bef07a05f062cb93a7dd61ba4b0694d4169f139 100644 (file)
--- a/.devops/llama-server-cuda.Dockerfile
+++ b/.devops/llama-server-cuda.Dockerfile
@@ -30,8 +30,10 @@ RUN make -j$(nproc) llama-server
 FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
 
 RUN apt-get update && \
-    apt-get install -y libcurl4-openssl-dev libgomp1
+    apt-get install -y libcurl4-openssl-dev libgomp1 curl
 
 COPY --from=build /app/llama-server /llama-server
 
+HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
+
 ENTRYPOINT [ "/llama-server" ]

diff --git a/.devops/llama-server-intel.Dockerfile b/.devops/llama-server-intel.Dockerfile
index cec43645233d14727ffc69f766c62f88889170d6..3bf1670ec40a4b354a7396163ecf494bffe9892f 100644 (file)
--- a/.devops/llama-server-intel.Dockerfile
+++ b/.devops/llama-server-intel.Dockerfile
@@ -20,10 +20,12 @@ RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
 FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
 
 RUN apt-get update && \
-    apt-get install -y libcurl4-openssl-dev
+    apt-get install -y libcurl4-openssl-dev curl
 
 COPY --from=build /app/build/bin/llama-server /llama-server
 
 ENV LC_ALL=C.utf8
 
+HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
+
 ENTRYPOINT [ "/llama-server" ]

diff --git a/.devops/llama-server-rocm.Dockerfile b/.devops/llama-server-rocm.Dockerfile
index f88cf20e5b9813a904c97d964a4ed2329343c62f..4b1cdc32090e6fac23c26dac3e0a877240c092c1 100644 (file)
--- a/.devops/llama-server-rocm.Dockerfile
+++ b/.devops/llama-server-rocm.Dockerfile
@@ -43,8 +43,10 @@ ENV CXX=/opt/rocm/llvm/bin/clang++
 # Enable cURL
 ENV LLAMA_CURL=1
 RUN apt-get update && \
-    apt-get install -y libcurl4-openssl-dev
+    apt-get install -y libcurl4-openssl-dev curl
 
 RUN make -j$(nproc) llama-server
 
+HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
+
 ENTRYPOINT [ "/app/llama-server" ]

diff --git a/.devops/llama-server-vulkan.Dockerfile b/.devops/llama-server-vulkan.Dockerfile
index b0fa0b8e656b57123e97078de4a9f3e7f9c4f43b..2bc2e45d3d676230fcfc3c98383984d38fa6d0b6 100644 (file)
--- a/.devops/llama-server-vulkan.Dockerfile
+++ b/.devops/llama-server-vulkan.Dockerfile
@@ -5,15 +5,11 @@ FROM ubuntu:$UBUNTU_VERSION as build
 # Install build tools
 RUN apt update && apt install -y git build-essential cmake wget
 
-# Install Vulkan SDK
+# Install Vulkan SDK and cURL
 RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
     wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
     apt update -y && \
-    apt-get install -y vulkan-sdk
-
-# Install cURL
-RUN apt-get update && \
-    apt-get install -y libcurl4-openssl-dev
+    apt-get install -y vulkan-sdk libcurl4-openssl-dev curl
 
 # Build it
 WORKDIR /app
@@ -28,4 +24,6 @@ RUN cp /app/build/bin/llama-server /llama-server && \
 
 ENV LC_ALL=C.utf8
 
+HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
+
 ENTRYPOINT [ "/llama-server" ]

diff --git a/.devops/llama-server.Dockerfile b/.devops/llama-server.Dockerfile
index aa93369bebebe5c10d9ea22f9151618b85f46475..a53a5c999c8cd6be1239ba9de221bcd01c65c560 100644 (file)
--- a/.devops/llama-server.Dockerfile
+++ b/.devops/llama-server.Dockerfile
@@ -3,7 +3,7 @@ ARG UBUNTU_VERSION=22.04
 FROM ubuntu:$UBUNTU_VERSION as build
 
 RUN apt-get update && \
-    apt-get install -y build-essential git libcurl4-openssl-dev
+    apt-get install -y build-essential git libcurl4-openssl-dev curl
 
 WORKDIR /app
 
@@ -22,4 +22,6 @@ COPY --from=build /app/llama-server /llama-server
 
 ENV LC_ALL=C.utf8
 
+HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
+
 ENTRYPOINT [ "/llama-server" ]