hf_text-generation-inference/server/Makefile-fbgemm

14 lines
749 B
Plaintext

fbgemm_commit := ddac8dd9fc0bee70a3f456df68b8aac38576c856
build-fbgemm:
git clone https://github.com/pytorch/FBGEMM.git fbgemm && \
cd fbgemm && git fetch && git checkout $(fbgemm_commit) && \
git submodule update --init --recursive && \
cd fbgemm_gpu && \
pip install -r requirements.txt && \
CUDA_ARCH_LIST="8.0;9.0a" NVCC_GENCODE="-gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_90a,code=sm_90a" TORCH_CUDA_ARCH_LIST="8.0;9.0a" python setup.py --package_variant genai build
install-fbgemm: build-fbgemm
cd fbgemm/fbgemm_gpu && \
CUDA_ARCH_LIST="8.0;9.0a" NVCC_GENCODE="-gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_90a,code=sm_90a" TORCH_CUDA_ARCH_LIST="8.0;9.0a" python setup.py --package_variant genai install