Pinned Repositories
comsoftwhu.github.io
The comsoft group in Wuhan University
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
CHESS
llama.cpp
Port of Facebook's LLaMA model in C/C++
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
whisper.cpp
Port of OpenAI's Whisper model in C/C++
ZeonfaiHo's Repositories
ZeonfaiHo/CHESS
ZeonfaiHo/llama.cpp
Port of Facebook's LLaMA model in C/C++
ZeonfaiHo/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
ZeonfaiHo/PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
ZeonfaiHo/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
ZeonfaiHo/whisper.cpp
Port of OpenAI's Whisper model in C/C++