hanrui1sensetime

Atom

Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.

GPTQ-for-PULSE

4 bits quantization of PULSE models using GPTQ

llm-awq

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLM

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

mmdeploy

MMDeployX-prototype

The prototype of MMDeployX

mmyolo

OpenMMLab YOLO series toolbox and benchmark

PoseTracker-Android-Prototype

PoseTracker Android Demo Prototype.

hanrui1sensetime/PoseTracker-Android-Prototype

PoseTracker Android Demo Prototype.

hanrui1sensetime/MMDeployX-prototype

The prototype of MMDeployX

hanrui1sensetime/GPTQ-for-PULSE

4 bits quantization of PULSE models using GPTQ

hanrui1sensetime/mmdeploy

hanrui1sensetime/mmyolo

OpenMMLab YOLO series toolbox and benchmark

hanrui1sensetime/Atom

Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

hanrui1sensetime/AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.

hanrui1sensetime/llm-awq

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

hanrui1sensetime/lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLM

hanrui1sensetime/mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

hanrui1sensetime/mmclassification

OpenMMLab Image Classification Toolbox and Benchmark

hanrui1sensetime/mmdeploy-javaapi-testdata

hanrui1sensetime/MMDeployX-APK

APK resources of MMDeploy-X

hanrui1sensetime/mmdetection

OpenMMLab Detection Toolbox and Benchmark

hanrui1sensetime/mmediting

OpenMMLab Image and Video Restoration, Editing and Generation Toolbox

hanrui1sensetime/mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

hanrui1sensetime/mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.

hanrui1sensetime/ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

hanrui1sensetime/OmniQuant

OmniQuant is a simple and powerful quantization technique for LLMs.

hanrui1sensetime/PaddleVideo

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

hanrui1sensetime/QUIK

Repository for the QUIK project, enabling the use of 4bit kernels for generative inference

hanrui1sensetime/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.