diff --git a/.devops/llama-cuda.Dockerfile b/.devops/llama-cuda.Dockerfile
index c2a3914ed..d5ce538f6 100644
--- a/.devops/llama-cuda.Dockerfile
+++ b/.devops/llama-cuda.Dockerfile
@@ -23,7 +23,7 @@ ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
 # Enable CUDA
 ENV LLAMA_CUDA=1
 
-RUN make -j$(nproc) llama
+RUN make -j$(nproc) llama-cli
 
 FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
 
diff --git a/.devops/llama-rocm.Dockerfile b/.devops/llama-rocm.Dockerfile
index 86b11b07f..7e8a6f0fa 100644
--- a/.devops/llama-rocm.Dockerfile
+++ b/.devops/llama-rocm.Dockerfile
@@ -40,6 +40,6 @@ ENV LLAMA_HIPBLAS=1
 ENV CC=/opt/rocm/llvm/bin/clang
 ENV CXX=/opt/rocm/llvm/bin/clang++
 
-RUN make -j$(nproc) llama
+RUN make -j$(nproc) llama-cli
 
 ENTRYPOINT [ "/app/llama-cli" ]
diff --git a/.devops/llama.Dockerfile b/.devops/llama.Dockerfile
index 21fdf2a66..38382bfc9 100644
--- a/.devops/llama.Dockerfile
+++ b/.devops/llama.Dockerfile
@@ -9,7 +9,7 @@ WORKDIR /app
 
 COPY . .
 
-RUN make -j$(nproc) llama
+RUN make -j$(nproc) llama-cli
 
 FROM ubuntu:$UBUNTU_VERSION as runtime
 
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 98e5244cb..e737ebeb3 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -240,7 +240,7 @@ jobs:
           echo "Fetch llama2c model"
           wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
           ./bin/convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
-          ./bin/llama -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
+          ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
 
       - name: Determine tag name
         id: tag