[Installation]: Is Branch v0.4.0.post1-rocm available for rocm-5.7?

[fangtaosong]

Your current environment

[pip3] numpy==1.26.4
[pip3] pytorch-triton-rocm==2.2.0
[pip3] torch==2.2.2+rocm5.7
[pip3] torchaudio==2.2.2+rocm5.7
[pip3] torchvision==0.17.2+rocm5.7
[conda] mkl                       2024.1.0                 pypi_0    pypi
[conda] mkl-include               2024.1.0                 pypi_0    pypi
[conda] numpy                     1.26.4                   pypi_0    pypi
[conda] pytorch-triton-rocm       2.2.0                    pypi_0    pypi
[conda] torch                     2.2.2+rocm5.7            pypi_0    pypi
[conda] torchaudio                2.2.2+rocm5.7            pypi_0    pypi
[conda] torchvision               0.17.2+rocm5.7           pypi_0    pypiROCM Version: 5.7.31921-d1770ee1b
Neuron SDK Version: N/A
vLLM Version: 0.4.0.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

How you are installing vllm

python setup.py install

[fangtaosong]

When linking HIP shared module xxx/vllm-rocm/build/lib.linux-x86_64-cpython-310/vllm/_C.cpython-310-x86_64-linux-gnu.so, operation failed and got duplicate symbol error.

ld.lld: error: duplicate symbol: __double2bfloat16(double)
>>> defined at amd_hip_bf16.h:209 (/opt/rocm-5.7.0/include/hip/amd_detail/amd_hip_bf16.h:209)
>>>            CMakeFiles/_C.dir/csrc/cache_kernels.hip.o:(__double2bfloat16(double))
>>> defined at amd_hip_bf16.h:209 (/opt/rocm-5.7.0/include/hip/amd_detail/amd_hip_bf16.h:209)
>>>            CMakeFiles/_C.dir/csrc/layernorm_kernels.hip.o:(.text+0x60)