Pinned Repositories
flash-attention
Fast and memory-efficient exact attention
FlagGems
FlagGems is an operator library for large language models implemented in Triton Language.
oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
oneflow-mlu
flash-attention
Fast and memory-efficient exact attention
Larva
oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
pingzhuu
Config files for my GitHub profile.
Larva
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
pingzhuu's Repositories
pingzhuu/flash-attention
Fast and memory-efficient exact attention
pingzhuu/Larva
pingzhuu/oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
pingzhuu/pingzhuu
Config files for my GitHub profile.
pingzhuu/JD_Sign_Action
基于github actions的京东自动化签到