ipconfigme

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

vllm

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

surrealdb

A scalable, distributed, collaborative, document-graph database, for the realtime web

Chat2DB

🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.

LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

quickwit

Cloud-native search engine for observability. An open-source alternative to Datadog, Elasticsearch, Loki, and Tempo.

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

lance

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, with more integrations coming..

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

LLaMA2-Accessory

An Open-source Toolkit for LLM Development

LLM-Agent-Survey

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

deforum-stable-diffusion

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

CUDA-Learn-Notes

🎉 Modern CUDA Learn Notes with PyTorch: fp32, fp16, bf16, fp8/int8, flash_attn, sgemm, sgemv, warp/block reduce, dot, elementwise, softmax, layernorm, rmsnorm.

LookaheadDecoding

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

streaming

A Data Streaming Library for Efficient Neural Network Training

DiskANN

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

data-centric-AI

A curated, but incomplete, list of data-centric AI resources.

efficient-dl-systems

Efficient Deep Learning Systems course materials (HSE, YSDA)

AIDB

ai4db and db4ai work

MatrixSlow

A simple deep learning framework in pure python for purpose of learning in DL

llm-pddl

puck

Puck is a high-performance ANN search engine

DistServe

Disaggregated serving system for Large Language Models (LLMs).

BinaryVectorDB

Efficient vector database for hundred millions of embeddings.

bitalosdb

Bitalosdb is a high-performance KV storage engine.

erasure-coding-durability

Python code to calculate the durability of data stored with erasure coding, such as Reed-Solomon.

accelerator-solution-zoo

Intel accelerators Zoo, like one of its solution Intel® Vector Data Streaming Library, it's a zoo of solutions based on Intel 4th Xeon processor or later HW accelerators, such as DSA, IAA, DLB,QAT and etc.

MINI-TORCH

Mini-pytorch implemented from scratch using Python