codefuse-ai/FasterTransformer4CodeFuse
High-performance LLM inference based on our optimized version of FastTransfomer
C++NOASSERTION
Issues
- 2
- 4
Error of try running model on 2GPUs
#5 opened by horcruxen - 1
- 1
cmake -DCMAKE_BUILD_TYPE=Release -DSM="80;75" -DBUILD_PYT=ON -DSPARSITY_SUPPORT=OFF -DMEASURE_BUILD_TIME=ON \ -DBUILD_CUTLASS_MIXED_GEMM=ON -DBUILD_MULTI_GPU=ON -DBUILD_TRT=OFF \ -DENABLE_FP8=OFF -DBUILD_PYBIND=ON -DTORCH_PYTHON_LIBRARIES=${TORCH_PYTHON _LIBRARIES} .. _LIBRARIES} ..
#4 opened by quida01 - 2
为什么huggingface的模型404了
#1 opened by Cuihongsen - 1
下载的模型文件 md5不对
#2 opened by sfss5362