Leonslam

Results 4 comments of Leonslam

The second one is x and the third one is y, the others are not used in the program.

> 经过调整端侧的配置,已成功运行。 请问你最终能在MNN里使用QNN运行LLM吗

> > Per the doc, we only support v73 architectures and above, so that device is unlikely to work. > > [@kory](https://github.com/kory) thank you for reply. we found llama3.2 1b...

I try to deploy llama3.2 1b on v68 8295p, get errors like: atlas:/data/local/tmp/llama/genie_bundle # ./genie-t2t-run -c genie_config.json -p "hello" /genie-t2t-run -c genie_config.json -p "hello" < Using libGenie.so version 1.11.0 [INFO]...