zhouwg

it was defined in latest source code from project ([rockchip-linux-mpp/osal/inc/mpp_common.h](https://github.com/rockchip-linux/mpp/blob/develop/osal/inc/mpp_common.h#L170)) as following: ``` #define SZ_1K (1024) #define SZ_2K (SZ_1K*2) #define SZ_4K (SZ_1K*4) #define SZ_8K (SZ_1K*8) #define SZ_16K (SZ_1K*16) #define SZ_32K...

copy directory "build" from project [rockchip-linux-mpp](https://github.com/rockchip-linux/mpp/tree/develop/build) manually and it woks as expected

vpu.h could be found at latest source code in project [rockchip-linux-mpp](https://github.com/rockchip-linux/mpp/blob/develop/inc/vpu.h). modify mpp_linux_cpp manually and it works as expected.

> ggml_backend_sched thanks for your comment. I'll try it whether ggml_backend_sched can cover the above scenarios. I think the method in this PR is more clear/straight before I study more...

> Currently it has some limitations that I suspect would prevent using it with backends that only implement a small subset of operations. However, it was designed from the first...

there is a issue in Github CI, Can someone from CI team take a look at this issue? thanks. 

@abb128 , thanks so much.it's very helpful for this [PoC](https://github.com/cdeos/kantv/issues/64) performance of real-time transcription on Xiaomi14 was improved **very significantly** before fine-tune:  after fine-tune: ![Screenshot from...

breakdown task(gradual refinement through Agile method and any help(from AI expert, from upstream GGML community, from Qualcomm, ......) are both greatly welcomed. Guidance from domain-expert is greatly appreciated if there...

background study: 1. QNN SDK: there are two types of AI SDK provided by Qualcomm, the QNN (aka Qualcomm® AI Engine Direct) SDK will be used in this PoC(guidance from...

updated on 03-30-2024,19:14, PoC-S21 & PoC-S22 done did NOT touch anything core stuff in this commit just an integration/troubleshooting work. challenge might be happened in next step.