make: *** [Make:55: release_build] Error 255

[MustaphaU]

Device: Win 11; RTX 4090

When I run: make -C docker release_build it fails with the error below.

make: Entering directory '/home/mustapham/TensorRT-LLM/docker'
Building docker image: tensorrt_llm/release:latest
DOCKER_BUILDKIT=1 docker build --pull  \
        --progress auto \
         --build-arg BASE_IMAGE=nvcr.io/nvidia/pytorch \
         --build-arg BASE_TAG=23.12-py3 \
         --build-arg BUILD_WHEEL_ARGS="--clean --trt_root /usr/local/tensorrt --python_bindings --benchmarks" \
         --build-arg TORCH_INSTALL_TYPE="skip" \
         \
         \
         \
         \
         \
         --build-arg TRT_LLM_VER="0.8.0.dev20240123" \
         \
         --build-arg GIT_COMMIT="b57221b764bc579cbb2490154916a871f620e2c4" \
         --target release \
        --file Dockerfile.multi \
        --tag tensorrt_llm/release:latest \
        ..
[+] Building 738.0s (28/39)                                                                              docker:default
 => CACHED [devel  3/14] COPY docker/common/install_cmake.sh install_cmake.sh                                      0.0s
 => CACHED [devel  4/14] RUN bash ./install_cmake.sh && rm install_cmake.sh                                        0.0s
 => CACHED [devel  5/14] COPY docker/common/install_ccache.sh install_ccache.sh                                    0.0s
 => CACHED [devel  6/14] RUN bash ./install_ccache.sh && rm install_ccache.sh                                      0.0s
 => CACHED [devel  7/14] COPY docker/common/install_tensorrt.sh install_tensorrt.sh                                0.0s
 => CACHED [devel  8/14] RUN bash ./install_tensorrt.sh     --TRT_VER=${TRT_VER}     --CUDA_VER=${CUDA_VER}     -  0.0s
 => CACHED [devel  9/14] COPY docker/common/install_polygraphy.sh install_polygraphy.sh                            0.0s
 => CACHED [devel 10/14] RUN bash ./install_polygraphy.sh && rm install_polygraphy.sh                              0.0s
 => CACHED [devel 11/14] COPY docker/common/install_mpi4py.sh install_mpi4py.sh                                    0.0s
 => CACHED [devel 12/14] RUN bash ./install_mpi4py.sh && rm install_mpi4py.sh                                      0.0s
 => CACHED [devel 13/14] COPY docker/common/install_pytorch.sh install_pytorch.sh                                  0.0s
 => CACHED [devel 14/14] RUN bash ./install_pytorch.sh skip && rm install_pytorch.sh                               0.0s
 => CACHED [release  1/11] WORKDIR /app/tensorrt_llm                                                               0.0s
 => CACHED [wheel 1/9] WORKDIR /src/tensorrt_llm                                                                   0.0s
 => CACHED [wheel 2/9] COPY benchmarks benchmarks                                                                  0.0s
 => CACHED [wheel 3/9] COPY cpp cpp                                                                                0.0s
 => CACHED [wheel 4/9] COPY benchmarks benchmarks                                                                  0.0s
 => CACHED [wheel 5/9] COPY scripts scripts                                                                        0.0s
 => CACHED [wheel 6/9] COPY tensorrt_llm tensorrt_llm                                                              0.0s
 => CACHED [wheel 7/9] COPY 3rdparty 3rdparty                                                                      0.0s
 => CACHED [wheel 8/9] COPY setup.py requirements.txt requirements-dev.txt ./                                      0.0s
 => [wheel 9/9] RUN python3 scripts/build_wheel.py --clean --trt_root /usr/local/tensorrt --python_bindings --b  736.3s
 => => # [ 94%] Building CUDA object tensorrt_llm/kernels/CMakeFiles/kernels_src.dir/decoderMaskedMultiheadAttention/de
 => => # coderMaskedMultiheadAttention64_half.cu.o
 => => # [ 94%] Building CUDA object tensorrt_llm/kernels/CMakeFiles/kernels_src.dir/decoderMaskedMultiheadAttention/de
 => => # coderMaskedMultiheadAttention80_bf16.cu.o
 => => # [ 94%] Building CUDA object tensorrt_llm/kernels/CMakeFiles/kernels_src.dir/decoderMaskedMultiheadAttention/de
 => => # coderMaskedMultiheadAttention80_float.cu.o
make: *** [Makefile:55: release_build] Error 255

[Shixiaowei02]

Please try changing an environment with more RAM. Thanks!

[MustaphaU]

Please try changing an environment with more RAM. Thanks!

Thanks @Shixiaowei02 My system specs are: Win 11: 64G RAM, and 24G VRAM (4090). Isn't this enough?

[Shixiaowei02]

Please use BUILD_WHEEL_ARGS to specify the number of build threads and try again. Thanks!

[MustaphaU]

Thanks @Shixiaowei02 I was able to build with docker on windows. Will close the issue now.