KYLN24

dclm

DataComp for Language Models

ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, MiniCPM, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, GraphRAG, DeepSpeed, vLLM, FastChat, Axolotl, etc.

Bend

A massively parallel, high-level programming language

datasets-viewer

A VSCode extension to preview Huggingface datasets quickly.

yyjson

The fastest JSON library in C

textgrad

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

langchain

🦜🔗 Build context-aware reasoning applications

agentscope

Start building LLM-empowered multi-agent applications in an easier way.

InternLM-WQX

AgentGym

Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

bilibot

A local chatbot fine-tuned by bilibili user comments.

amber

💎 Amber the programming language compiled to bash

sqlgym

uptime-kuma

A fancy self-hosted monitoring tool

ratchet

A cross-platform browser ML framework.

cortex

Drop-in, local AI alternative to the OpenAI stack. Multi-engine (llama.cpp, TensorRT-LLM, ONNX). Powers 👋 Jan

neural-speed

An innovative library for efficient LLM inference via low-bit quantization

dioxus

Fullstack app framework for web, desktop, mobile, and more.

HuixiangDou

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

min-sized-rust

🦀 How to minimize Rust binary size 📦

llamafile

Distribute and run LLMs with a single file.

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

garnet

Garnet is a remote cache-store from Microsoft Research that offers strong performance (throughput and latency), scalability, storage, recovery, cluster sharding, key migration, and replication features. Garnet can work with existing Redis clients.

MediaCrawler

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫

borgo

Borgo is a statically typed language that compiles to Go.

ParallelTokenizer

Use the tokenizer in parallel to achieve superior acceleration

typst.ts

Run Typst in JavaScriptWorld.

OpenDevin

🐚 OpenDevin: Code Less, Make More

sglang

SGLang is yet another fast serving framework for large language models and vision language models.