Pinned Repositories
awesome-model-compression-and-acceleration
a list of awesome papers on deep model ompression and acceleration
DFI
Deep Fault Injection(DFI) is a framework which can help you train,verify,quantize and fault-inject for your deep neural network(DNN) models fastly and concisely!
EmotiVoice-TensorRT
The faster EmotiVoice infer engine with ~8x speedup
fastllm
纯c++实现，无第三方依赖的大模型库，支持CUDA加速，目前支持国产大模型ChatGLM-6B，MOSS; 可以在安卓设备上流畅运行ChatGLM-6B
Neural-Networks-on-Chip
This is a collection of works on neural networks and neural accelerators.
NVpower
NVpower is a tool to measure the energy consumption of NVIDIA GPUs.
Paddle2ONNX
ONNX Model Exporter for PaddlePaddle
pymnn-llm
weekly-papers
wildkid1024
wildkid1024's Repositories
wildkid1024/EmotiVoice-TensorRT
The faster EmotiVoice infer engine with ~8x speedup
wildkid1024/weekly-papers
wildkid1024/pymnn-llm
wildkid1024/DFI
Deep Fault Injection(DFI) is a framework which can help you train,verify,quantize and fault-inject for your deep neural network(DNN) models fastly and concisely!
wildkid1024/fastllm
纯c++实现，无第三方依赖的大模型库，支持CUDA加速，目前支持国产大模型ChatGLM-6B，MOSS; 可以在安卓设备上流畅运行ChatGLM-6B
wildkid1024/awesome-model-compression-and-acceleration
a list of awesome papers on deep model ompression and acceleration
wildkid1024/Neural-Networks-on-Chip
This is a collection of works on neural networks and neural accelerators.
wildkid1024/NVpower
NVpower is a tool to measure the energy consumption of NVIDIA GPUs.
wildkid1024/Paddle2ONNX
ONNX Model Exporter for PaddlePaddle
wildkid1024/wildkid1024