hisrg / SNPE
Snapdragon Neural Processing Engine (SNPE) SDKThe Snapdragon Neural Processing Engine (SNPE) is a Qualcomm Snapdragon software accelerated runtime for the execution of deep neural networks. With SNPE, users can: Execute an arbitrarily deep neural network Execute the network on the SnapdragonTM CPU, the AdrenoTM GPU or the HexagonTM DSP. Debug t…
☆34Updated 3 years ago
Alternatives and similar repositories for SNPE:
Users that are interested in SNPE are comparing it to the libraries listed below
- ☆24Updated 2 years ago
- ☆40Updated 2 years ago
- 将MNN拆解的简易前向推理框架(for study!)☆22Updated 4 years ago
- An easy way to run, test, benchmark and tune OpenCL kernel files☆23Updated last year
- MegEngine到其他框架的转换器☆69Updated 2 years ago
- ☆24Updated 3 years ago
- Inference TinyLlama models on ncnn☆24Updated last year
- Tencent NCNN with added CUDA support☆69Updated 4 years ago
- A set of examples around MegEngine☆31Updated last year
- quantize aware training package for NCNN on pytorch☆70Updated 3 years ago
- Sample projects for InferenceHelper, a Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, ncnn, MNN,…☆20Updated 3 years ago
- NeRF in NCNN with c++ & vulkan☆67Updated last year
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆42Updated last year
- ☆32Updated 9 months ago
- ☆124Updated last year
- Implement ARM NEON intrinsics in C++☆21Updated 11 months ago
- the C++ version of Seq2Seq with ncnn☆23Updated 3 years ago
- Common libraries for PPL projects☆29Updated last month
- ☆84Updated 2 years ago
- ☆16Updated last month
- Count number of parameters / MACs / FLOPS for ONNX models.☆92Updated 6 months ago
- A converter for llama2.c legacy models to ncnn models.☆87Updated last year
- Tengine 管子是用来快速生产 demo 的辅助工具☆13Updated 3 years ago
- mperf是一个面向移动/嵌入式平台的算子性能调优工具箱☆183Updated last year
- ncnn和pnnx格式编辑器☆133Updated 7 months ago
- A tool convert TensorRT engine/plan to a fake onnx☆38Updated 2 years ago
- ncnn android benchmark app☆85Updated 3 years ago
- ☆20Updated 2 years ago
- c++ version of yolov7-mask with ncnn☆59Updated 2 years ago
- This is a demo how to write a high performance convolution run on apple silicon☆54Updated 3 years ago