Liu Xuechen comments

Repositories
Issues
Comments

Results 3 comments of


                                            Liu Xuechen

Does it support other DeepSeek models?

Dose it support deepseek-moe-16b-chat? Thanks

QWen3-0.6B NPU 部署，Convert for QNN, QualComn's NPU，Broad cast error

我在将qwen3-4b，qwen3-1.7b模型编译的时候遇到了相同的问题，我是编译成elite版本（--soc_id=69 --dsp_arch=v79），请问现在有办法解决吗？如果我忽略这个转换问题，直接在手机上运行llm_demo会出现segment_fault

Qwen3-4B crashes at "Prepare for tuning opt" with QNN HTP backend on Windows ARM64

> [@Qxinyu](https://github.com/Qxinyu) Just an update, we have tried running it on android NPU (Snapdragon 8 Gen3), by following similar steps as in case of Windows and it worked perfectly. Both...