GitHub Trending repo Aug 2

alikon-art/DeterminFlow: A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时:快速开发、验证和恢复复杂 AI 工作流,并将其稳定交付为服务。

A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时:快速开发、验证和恢复复杂 AI 工作流,并将其稳定交...

GitHub Trending repo Aug 2

Jit-Roy/weellm: WeeLLM is a layer-streaming inference engine for large diffusion models (FLUX.2, Z-Image-Turbo, SDXL, SD1.5) that runs on under 4GB VRAM with zero quantization, streaming one transformer layer at a time directly from Hugging Face safetensors files.

WeeLLM is a layer-streaming inference engine for large diffusion models (FLUX.2, Z-Image-Turbo, SDXL, SD1.5) that runs on under 4GB VRAM with zero quantization, streaming one trans...

GitHub Trending repo Aug 1

AFan4724/clone-chat: 用 AI 大模型复刻聊天对象的本地对话 Agent:导入真实聊天记录,LLM 学习 TA 的语气、表情和回复节奏并以人物身份延续对话,支持语音、主动联系与长期记忆,数据全在本地。 | Clone anyone's texting style from real chat history: a local-first LLM agent that learns their tone, stickers and reply rhythm, then chats as them — voice, proactive messages, long-term memory, fully private.

用 AI 大模型复刻聊天对象的本地对话 Agent:导入真实聊天记录,LLM 学习 TA 的语气、表情和回复节奏并以人物身份延续对话,支持语音、主动联系与长期记忆,数据全在本地。 | Clone anyone's texting style from real chat history: a local-first LLM agent that learns...