FlexGen: high-throughput generative inference of large language models with a single GPU

还行! 目前共计 47 篇日志。 继续努力。

2024

05-21

FlexGen: high-throughput generative inference of large language models with a single GPU

04-17

思维链

04-16

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

04-09

leetcode肝活

04-09

Jacobian矩阵

04-02

局部最优和鞍点

03-24

TinyLLM: Learning a Small Student from Multiple Large Language Models

03-18

Towards A Unified View Of Parameter-Efficient Transfer Learning

03-17

Hello World

03-06

softmax