From b7f5f46e03edbe73abb0784e27faa20efb8a42d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sigbj=C3=B8rn=20Skj=C3=A6ret?= Date: Fri, 12 Dec 2025 19:39:23 +0100 Subject: [PATCH] docker : include legacy llama-completion binary (#17964) --- .devops/cann.Dockerfile | 2 +- .devops/cpu.Dockerfile | 2 +- .devops/cuda.Dockerfile | 2 +- .devops/intel.Dockerfile | 2 +- .devops/musa.Dockerfile | 2 +- .devops/rocm.Dockerfile | 2 +- .devops/s390x.Dockerfile | 2 +- .devops/tools.sh | 8 ++++++-- .devops/vulkan.Dockerfile | 2 +- 9 files changed, 14 insertions(+), 10 deletions(-) diff --git a/.devops/cann.Dockerfile b/.devops/cann.Dockerfile index cd8f87b2ea..9d27e00fb1 100644 --- a/.devops/cann.Dockerfile +++ b/.devops/cann.Dockerfile @@ -111,7 +111,7 @@ ENTRYPOINT ["/app/tools.sh"] # ============================================================================== FROM base AS light -COPY --from=build /app/full/llama-cli /app +COPY --from=build /app/full/llama-cli /app/full/llama-completion /app ENTRYPOINT [ "/app/llama-cli" ] diff --git a/.devops/cpu.Dockerfile b/.devops/cpu.Dockerfile index 6e16ecda44..b9e84ab986 100644 --- a/.devops/cpu.Dockerfile +++ b/.devops/cpu.Dockerfile @@ -68,7 +68,7 @@ ENTRYPOINT ["/app/tools.sh"] ### Light, CLI only FROM base AS light -COPY --from=build /app/full/llama-cli /app +COPY --from=build /app/full/llama-cli /app/full/llama-completion /app WORKDIR /app diff --git a/.devops/cuda.Dockerfile b/.devops/cuda.Dockerfile index 54f793d0a3..fed5863157 100644 --- a/.devops/cuda.Dockerfile +++ b/.devops/cuda.Dockerfile @@ -74,7 +74,7 @@ ENTRYPOINT ["/app/tools.sh"] ### Light, CLI only FROM base AS light -COPY --from=build /app/full/llama-cli /app +COPY --from=build /app/full/llama-cli /app/full/llama-completion /app WORKDIR /app diff --git a/.devops/intel.Dockerfile b/.devops/intel.Dockerfile index d1a8fbed4c..adebf08229 100644 --- a/.devops/intel.Dockerfile +++ b/.devops/intel.Dockerfile @@ -73,7 +73,7 @@ ENTRYPOINT ["/app/tools.sh"] FROM base AS light COPY --from=build /app/lib/ /app -COPY --from=build /app/full/llama-cli /app +COPY --from=build /app/full/llama-cli /app/full/llama-completion /app WORKDIR /app diff --git a/.devops/musa.Dockerfile b/.devops/musa.Dockerfile index faa3500e61..34d6ad9f40 100644 --- a/.devops/musa.Dockerfile +++ b/.devops/musa.Dockerfile @@ -81,7 +81,7 @@ ENTRYPOINT ["/app/tools.sh"] ### Light, CLI only FROM base AS light -COPY --from=build /app/full/llama-cli /app +COPY --from=build /app/full/llama-cli /app/full/llama-completion /app WORKDIR /app diff --git a/.devops/rocm.Dockerfile b/.devops/rocm.Dockerfile index d6bf28b105..53c3ed8d88 100644 --- a/.devops/rocm.Dockerfile +++ b/.devops/rocm.Dockerfile @@ -94,7 +94,7 @@ ENTRYPOINT ["/app/tools.sh"] ### Light, CLI only FROM base AS light -COPY --from=build /app/full/llama-cli /app +COPY --from=build /app/full/llama-cli /app/full/llama-completion /app WORKDIR /app diff --git a/.devops/s390x.Dockerfile b/.devops/s390x.Dockerfile index b7c9457680..1e66f061d5 100644 --- a/.devops/s390x.Dockerfile +++ b/.devops/s390x.Dockerfile @@ -105,7 +105,7 @@ WORKDIR /llama.cpp/bin # Copy llama.cpp binaries and libraries COPY --from=collector /llama.cpp/bin/*.so /llama.cpp/bin -COPY --from=collector /llama.cpp/bin/llama-cli /llama.cpp/bin +COPY --from=collector /llama.cpp/bin/llama-cli /llama.cpp/bin/llama-completion /llama.cpp/bin ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ] diff --git a/.devops/tools.sh b/.devops/tools.sh index 8a3a693400..cc5ee17dfd 100755 --- a/.devops/tools.sh +++ b/.devops/tools.sh @@ -13,6 +13,8 @@ elif [[ "$arg1" == '--quantize' || "$arg1" == '-q' ]]; then exec ./llama-quantize "$@" elif [[ "$arg1" == '--run' || "$arg1" == '-r' ]]; then exec ./llama-cli "$@" +elif [[ "$arg1" == '--run-legacy' || "$arg1" == '-l' ]]; then + exec ./llama-completion "$@" elif [[ "$arg1" == '--bench' || "$arg1" == '-b' ]]; then exec ./llama-bench "$@" elif [[ "$arg1" == '--perplexity' || "$arg1" == '-p' ]]; then @@ -32,8 +34,10 @@ elif [[ "$arg1" == '--server' || "$arg1" == '-s' ]]; then else echo "Unknown command: $arg1" echo "Available commands: " - echo " --run (-r): Run a model previously converted into ggml" - echo " ex: -m /models/7B/ggml-model-q4_0.bin -p \"Building a website can be done in 10 simple steps:\" -n 512" + echo " --run (-r): Run a model (chat) previously converted into ggml" + echo " ex: -m /models/7B/ggml-model-q4_0.bin" + echo " --run-legacy (-l): Run a model (legacy completion) previously converted into ggml" + echo " ex: -m /models/7B/ggml-model-q4_0.bin -no-cnv -p \"Building a website can be done in 10 simple steps:\" -n 512" echo " --bench (-b): Benchmark the performance of the inference for various parameters." echo " ex: -m model.gguf" echo " --perplexity (-p): Measure the perplexity of a model over a given text." diff --git a/.devops/vulkan.Dockerfile b/.devops/vulkan.Dockerfile index fd7195c5be..b37b4f277d 100644 --- a/.devops/vulkan.Dockerfile +++ b/.devops/vulkan.Dockerfile @@ -68,7 +68,7 @@ ENTRYPOINT ["/app/tools.sh"] ### Light, CLI only FROM base AS light -COPY --from=build /app/full/llama-cli /app +COPY --from=build /app/full/llama-cli /app/full/llama-completion /app WORKDIR /app