#4792·MNN

已获得支持mtk npu 的最新仓库mnn3.6.0,使用neuropilot-sdk-basic-7.0.8-build20240807进行天玑9300/8300 llmexport.py导出后,使用neruonsdk 对第一层prompt编译报错

Author: dr3334Created Aug 20, 2026Updated Sep 11, 2026
Labelstype:bugplatform:androidmodule:llm

https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#mtk-llm step follow above link rope op not support

sin/cos
cast(int32 -> fp16)
mul 
unsupport op

error occur because io function _nupSupport

python

static bool _npuSupportOp(const Op* op) {
    if (gMaxKVSize > 0) {  
        return true;        
    }
    if (op->type() == OpType_Attention && attn->kv_cache())
        return false;
    if (op->type() == OpType_LinearAttention)
        return false;
    return true;
}

prefill -> dynamic rope decode -> static rope