hayyaw

ggml_vec_dot_f16's perf is slower servely when enable ARM_FEATURE_FP16_VECTOR_ARITHMETIC on Android

5

# Prerequisites Please answer the following questions for yourself before submitting an issue. - [x] I am running the latest code. Development is very rapid so there are no tagged...

来源为README中的示例： mperf::CpuCounterSet cpuset = "CYCLES,INSTRUCTIONS,..."; mperf::XPMU xpmu(cpuset); xpmu.run(); ... // add your function to be measured xpmu.sample(); xpmu.stop(); 使用时报错找不到，是否支持android机器cpu测试算子执行过程的 GFLOPs和 GBPs，如果支持，要如何测试？按现有文档说明会报错

报错Failed to get a file descriptor for ASE_SPEC是什么原因呢

3

terminating with uncaught exception of type mperf::MperfError: Failed to get a file descriptor for ASE_SPEC

### Feature request tflite exporter for decoder only llms such as tinyllama ### Motivation Some platforms only support full int8 op and full int8 tflite models can be deployed. Is...

QNN后端已经支持哪些模型了？是如何量化的

2

QNN后端后续规划是什么？现在还不支持LLM吗？在哪些模型上进行了验证？想测试下

### System Info ```shell main branch newest local pip install ``` ### Who can help? @michaelbenayoun ### Information - [X] The official example scripts - [ ] My own modified...