RYDE-WORK/MiniCPM
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/MiniCPM.git synced 2026-01-24 07:29:12 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README-en.md

Browse Source
This commit is contained in:
SillyXu 2024-02-05 20:05:26 +09:00 committed by GitHub
parent cd2ce5664f
commit 86b90c9d0d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README-en.md
View File

@ -345,7 +345,7 @@ print(res)
#### Performance
* We did not conduct in-depth optimization and system testing on the mobile inference model, only verifying the feasibility of MiniCPM using mobile phone chips for inference.
* There have been no previous attempts to deploy multimodal models on mobile phones. We have verified the feasibility of deploying MiniCPM-V on mobile phones based on MLC-LLM this time, and it can input and output normally. However, there also exist a problem of long image processing time, which needs further optimization :)
* Besides us, there are also some [efforts](https://github.com/ggerganov/llama.cpp/blob/master/examples/llava/MobileVLM-README.md) to deploy multimodal models on mobile phones based on llama.cpp. We have verified the feasibility of deploying MiniCPM-V on mobile phones based on MLC-LLM this time, and it can input and output normally. However, there also exist a problem of long image processing time, which needs further optimization :)
* **We welcome more developers to continuously improve the inference performance of LLMs on mobile phones and update the test results below.**
| Mobile Phones | OS | Processor | Memory（GB） | Inference Throughput（token/s） |