A high-throughput and memory-efficient inference and serving engine for LLMs

DeepEP: an efficient expert-parallel communication library

CUDA Templates for Linear Algebra Subroutines

A self-learning tutorail for CUDA High Performance Programing.

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)

OpenAI ChatGPT/GPT-4/GPT-3 SDK Go Client to Interact with the GPT-4/GPT-3 APIs.

Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification

Rank-1 89% (Single Query) on Market1501 with raw triplet loss, In Defense of the Triplet Loss for Person Re-Identification, using Pytorch

决策树实现 ID3算法 信息增益计算

2019届秋招面经集合