《动手学大模型Dive into LLMs》系列编程实践教程

Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.

DuckDB is an in-process SQL OLAP Database Management System

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Accessible large language models via k-bit quantization for PyTorch.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

The AI-native database built for LLM applications, providing incredibly fast full-text and vector search

A library that provides an embeddable, persistent key-value store for fast storage.

Llama3-Tutorial（XTuner、LMDeploy、OpenCompass）

a high-performance, large-capacity, multi-tenant, data-persistent, strong data consistency based on raft, Redis-compatible elastic KV data storage system based on RocksDB

Pika is a Redis-Compatible database developed by Qihoo's infrastructure team.

Fine-tuning LLMs using QLoRA

LLM inference in C/C++

Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs,…

Inference Llama 2 in one file of pure C

中文版rocksdb文档

personal chatgpt

Attention is all you need implementation

Well documented, unit tested, type checked and formatted implementation of a vanilla transformer - for educational purposes.

pytorch distribute tutorials

Natural Language Processing Tutorial for Deep Learning Researchers

RocksDB Replication

A library for building and serving multi-node distributed faiss indices.

Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes)

QLoRA: Efficient Finetuning of Quantized LLMs

A RocksDB compatible KV storage engine with better performance