Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
hf_text-generation-inference/server/Makefile-fbgemm

16 lines
883 B
Plaintext
Raw Normal View History

feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) * feat(fp8): add support for fbgemm * allow loading fp8 weights directly * update outlines * fix makefile * build fbgemm * avoid circular import and fix dockerfile * add default dtype * refactored weights loader * fix auto conversion * fix quantization config parsing * force new nccl on install * missing get_weights implementation * increase timeout
2024-07-20 11:02:04 -06:00
fbgemm_commit := 9cf0429b726931cfab72b8264730bea682f32fca
build-fbgemm:
chmod +x fix_torch90a.sh && ./fix_torch90a.sh && \
git clone https://github.com/pytorch/FBGEMM.git fbgemm && \
cp fbgemm_remove_unused.patch fbgemm && \
cd fbgemm && git fetch && git checkout $(fbgemm_commit) && git apply fbgemm_remove_unused.patch && \
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