[arXiv'24 & NeurIPSW'24] MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

A modular graph-based Retrieval-Augmented Generation (RAG) system

REST: Retrieval-Based Speculative Decoding, NAACL 2024

PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

📚150+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

📖A curated list of Awesome LLM/VLM Inference Papers with codes, such as FlashAttention, PagedAttention, Parallelism, etc. 🎉🎉

A high-throughput and memory-efficient inference and serving engine for LLMs

[Arxiv] Aligning Modalities in Vision Large Language Models via Preference Fine-tuning

The official Meta Llama 3 GitHub site

Milvus is a high-performance, cloud-native vector database designed to scale vector search.

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

[EMNLP'24] RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Ollama 기반의 int4 gguf 형식 sLLM을 multi-turn 형태로 대화할 수 있는 통합 모듈

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)

LangChain 공식 Document, Cookbook, 그 밖의 실용 예제를 바탕으로 작성한 한국어 튜토리얼입니다. 본 튜토리얼을 통해 LangChain을 더 쉽고 효과적으로 사용하는 방법을 배울 수 있습니다.

Ongoing research training gaussian splatting at scale by distributed system

[CVPR 2024 (Highlight)] Relightable and Animatable Neural Avatar from Sparse-View Video

A curated list of retrieval-augmented generation (RAG) in large language models

AI 법률 어드바이저 모델 : KoAlpaca 모델에 생활법령 데이터를 학습시켜 LoRA finetuning & 생활 법령 100문 100답 데이터 2,195개를 스크랩 하여 LLM 학습을 위한 대화 형식의 json 파일로 제작

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds