Pinned Repositories
Binarynet
Xornet's tensorflow implementation
caffe-adas
caffe development kit extended by fabu inc
ControlNet
Let us control diffusion models!
deep-docker
some scripts for my docker
EasyQuant
EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.
nas-pruning-quantize
SNQR--how to improve the performance of binary network
NAS-WDAN
Weaved deep aggregation network based on NAS
pytorch-quantity
An 8bit automated quantization conversion tool for the pytorch (Post-training quantization based on KL divergence)
tensorflow-quantity
An 8bit automated quantization conversion tool for the tensorflow (Post-training quantization based on KL divergence)
tensorflow-refmodel
Based on the trained model and the customized structure, 8bit quantization weight is generated for the chip, and quantization accuracy is output
lswzjuer's Repositories
lswzjuer/ControlNet
Let us control diffusion models!
lswzjuer/ABQ-LLM
lswzjuer/awesome-aigc
A list of awesome AIGC works
lswzjuer/awesome-transformer-search
A curated list of awesome resources combining Transformers with Neural Architecture Search
lswzjuer/Baichuan2
A series of large language models developed by Baichuan Intelligent Technology
lswzjuer/benchmarking-gnns
Repository for benchmarking graph neural networks
lswzjuer/CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
lswzjuer/CUDA-Learn-Note
🎉CUDA 笔记 / 高频面试题汇总 / C++笔记，个人笔记，更新随缘: sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
lswzjuer/cuda-tensorcore-hgemm
lswzjuer/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
lswzjuer/EfficientFormer
lswzjuer/ELITE
Official Implementation of "ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation"
lswzjuer/flash-attention
Fast and memory-efficient exact attention
lswzjuer/flashinfer
FlashInfer: Kernel Library for LLM Serving
lswzjuer/maple-diffusion
Stable Diffusion inference on iOS / macOS using MPSGraph
lswzjuer/ml-cvnets
CVNets: A library for training computer vision networks
lswzjuer/MobileVLM
MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices
lswzjuer/nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
lswzjuer/oneflow
OneFlow is a performance-centered and open-source deep learning framework.
lswzjuer/PerceptualSimilarity
LPIPS metric. pip install lpips
lswzjuer/q-diffusion
[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
lswzjuer/sima
Official implementation for "SimA: Simple Softmax-free Attention for Vision Transformers"
lswzjuer/SparseByteNN
SparseByteNN: A Novel Mobile Inference Acceleration Framework Based on Fine-Grained Group Sparsity
lswzjuer/speculative-decoding
Explorations into some recent techniques surrounding speculative decoding
lswzjuer/stable-diffusion
A latent text-to-image diffusion model
lswzjuer/Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
lswzjuer/SwinIR
SwinIR: Image Restoration Using Swin Transformer (official repository)
lswzjuer/TPAT
TensorRT Plugin Autogen Tool
lswzjuer/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
lswzjuer/x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers