Gaze/ChatGLM2-6B
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update README.md

Browse Source 
Add fastllm
This commit is contained in:
Qinkai 2023-07-04 16:41:01 +08:00 committed by GitHub
parent b99e3d74c9
commit b5632d5ea1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -29,6 +29,7 @@ ChatGLM2-6B 开源模型旨在与开源社区一起推动大模型技术发展
## 友情链接
对 ChatGLM2 进行加速的开源项目：
* [fastllm](https://github.com/ztxz16/fastllm/): 全平台加速推理方案，单GPU每秒可达10000+token，手机端最低3G内存实时运行（骁龙865上约4~5 token/s）
* [chatglm.cpp](https://github.com/li-plus/chatglm.cpp): 类似 llama.cpp 的 CPU 量化加速推理方案，实现 Mac 笔记本上实时对话
## 评测结果