Kuan Wu's starred repositories
flash-attention
Fast and memory-efficient exact attention
Baichuan-7B
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
GroundingDINO
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Segment-Everything-Everywhere-All-At-Once
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
transformer-deploy
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
lang-segment-anything
SAM with text prompt
segment-anything-fast
A batched offline inference oriented version of segment-anything
llm-search
Querying local documents, powered by LLM
sft_datasets
开源SFT数据集整理,随时补充
segment_anything_tensorrt
Accelerate segment anything model inference using Tensorrt 8.6.1.6
BYZER-RETRIEVAL
Byzer-retrieval is a distributed retrieval system which designed as a backend for LLM RAG (Retrieval Augmented Generation). The system supports both BM25 retrieval algorithm and vector retrieval algorithm.
triton-server
triton server with segment anything(SAM)