Guoming Yang's starred repositories
pytorch_block_sparse
Fast Block Sparse Matrices for Pytorch
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
FP8-Emulation-Toolkit
PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.
RISC-V-32I
体系结构课程实验:RISC-V 32I 流水线 CPU,实现37条指令,转发,冒险检测,Cache,分支预测器