diff --git a/Dockerfile_llamacpp b/Dockerfile_llamacpp index 1f55cf82..4b7dacd3 100644 --- a/Dockerfile_llamacpp +++ b/Dockerfile_llamacpp @@ -48,11 +48,11 @@ FROM deps AS builder COPY --from=planner /app/recipe.json recipe.json RUN cargo chef cook \ --recipe-path recipe.json \ - --profile release-opt \ + --profile release \ --package text-generation-router-llamacpp COPY . . RUN cargo build \ - --profile release-opt \ + --profile release \ --package text-generation-router-llamacpp --frozen FROM nvidia/cuda:12.8.0-cudnn-runtime-ubuntu24.04 @@ -69,7 +69,7 @@ RUN pip3 install --no-cache-dir -r requirements.txt COPY --from=builder /usr/lib/libllama.so /usr/lib/ COPY --from=builder /usr/lib/libggml*.so /usr/lib/ -COPY --from=builder /app/target/release-opt/text-generation-router-llamacpp /usr/bin/ +COPY --from=builder /app/target/release/text-generation-router-llamacpp /usr/bin/ ENV HF_HUB_ENABLE_HF_TRANSFER=1