无溯·曾's repositories
Digital-Infrastructure
数字底座是一款面向大型政府、企业数字化转型,基于身份认证、组织架构、岗位职务、应用系统、资源角色等功能构建的统一且安全的管理支撑平台。数字底座基于三员管理模式,具备微服务、多租户、容器化和国产化,支持用户利用代码生成器快速构建自己的业务应用,同时可关联诸多成熟且好用的内部生态应用
im-server
A high-performance IM server.
dynamicPDB
Dynamic PDB datasets
Awesome-LLMs-on-device
Awesome LLMs on Device: A Comprehensive Survey
nexa-sdk
Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.
mini-omni
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Bench2Drive
Closed-loop multi-ability evaluation of end-to-end autonomous driving algorithms
AIGenerateCode
Android马甲包-垃圾代码-混淆
MateGen
Next-Generation Interactive Intelligent Programming Assistant
cocos-engine
Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D games and instant web entertainment.
ADI-Stable-Diffusion
Accelerate your Stable Diffusion inference with the library's universal C/C++ framework design, powered by ONNXRuntime & across platforms.
freechat
https://freechat.fun
LLMEPET
[MM'24 Oral] Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
cube-studio
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台,支持sso登录,多租户,大数据平台对接,notebook在线开发,拖拉拽任务流pipeline编排,多机多卡分布式训练,超参搜索,推理服务VGPU,边缘计算,serverless,标注平台,自动化标注,数据集管理,大模型微调,vllm大模型推理,llmops,私有知识库,AI模型应用商店,支持模型一键开发/推理/微调,支持国产cpu/gpu/npu芯片,支持RDMA,支持pytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/spark/ray/volcano分布式
Juggle
一款适用于微服务编排,第三方api集成,私有化定制开发,编写BFF聚合层等场景的强大低码编排工具!
champ
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
CBGBench
Official code repository of CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
dingo
A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.
Cybersecurity-Doughnuts
Fullstack engineer's checklist for your cybersecurity.
kindling
eBPF-based Cloud Native Monitoring Tool
AudioLCM
PyTorch Implementation of [AudioLCM]: a efficient and high-quality text-to-audio generation with latent consistency model.
hallo
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
CSGHub
CSGHub is an opensource large model assets platform just like on-premise huggingface which helps to manage datasets, model files, codes and more. CSGHub是一个开源、可信的大模型资产管理平台,可帮助用户治理LLM和LLM应用生命周期中涉及到的资产(数据集、模型文件、代码等)。CSGHub提供类似私有化的Huggingface功能,以类似OpenStack Glance管理虚拟机镜像、Harbor管理容器镜像以及Sonatype Nexus管理制品的方式,实现对LLM资产的管理。欢迎关注反馈和Star⭐️
OmDet
Real-time and accurate open-vocabulary end-to-end object detection
Open-ReplaceAnything
Unofficial Implementation of ReplaceAnything: https://aigcdesigngroup.github.io/replace-anything/
DeepBI
LLM based data scientist, AI native data application. AI-driven infinite thinking redefines BI.
WavCraft
Official repo for WavCraft, an AI agent for audio creation and editing