caonann

Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

spreadsheet-is-all-you-need

A nanoGPT pipeline packed in a spreadsheet

x-ui

支持多协议多用户的 xray 面板

nilaway

Static analysis tool to detect potential nil panics in Go code

HunyuanDiT

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

open-webui

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

sanitizers

AddressSanitizer, ThreadSanitizer, MemorySanitizer

CacheLib

Pluggable in-process caching engine to build and scale high performance services

envoy

Cloud-native high-performance edge/middle/service proxy

Mongoku

🔥The Web-scale GUI for MongoDB

dask

Parallel computing with task scheduling

ants

🐜🐜🐜 ants is a high-performance and low-cost goroutine pool in Go.

transformer-debugger

air

☁️ Live reload for Go apps

rtp-llm

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

EMO

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

deploy

Pandora Cloud + Pandora Server + Shared Chat + BackendAPI Proxy + Chat2API + Signup Free = PandoraNext. New GPTs(Gizmo) UI, All in one!

Yi

A series of large language models trained from scratch by developers @01-ai

mywords

背单词神器。 输入一个英语或双语文章的网址，本工具将自动提取文章中所有单词及其所在句子，对文章单词进行去重、统计汇总。你可以过滤筛选只显示出你不认识的单词。

screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

DocsGPT

GPT-powered chat for documentation, chat with your documents

gpt-newspaper

GPT based autonomous agent designed to create personalized newspapers tailored to user preferences.

search_with_lepton

Building a quick conversation-based search demo with Lepton AI.

zed

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

inferflow

Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

TANet-image-aesthetics-and-quality-assessment

[IJCAI 2022, Official Code] for paper "Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks". Official Weights and Demos provided. 首个面向多主题场景的美学评估数据集、算法和benchmark.

Orion

Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. Orion-14B 系列模型包括一个具有140亿参数的多语言基座大模型以及一系列相关的衍生模型，包括对话模型，长文本模型，量化模型，RAG微调模型，Agent微调模型等。

lm-evaluation-harness

A framework for few-shot evaluation of language models.