streaming-llm 开源项目推荐（8 个）

FonaTech /Project_Chronos

⚡ 通过前瞻预测和异步DMA预取进行零停滞MoE推断。针对 SSD 输入输出优化，采用混合 MLA+滑动窗口关注。

Mattral /SimulatedSelf

A real-time, browser-native digital twin: your webcam drives a 3D humanoid that mirrors your pose, reads your emotion, and chats back through a streaming Llama 3.1 voice pipeline.

ber4444 /compose-multiplatform-chess

Multiplatform 3D chess app powered by Stockfish, featuring on-device AI move coaching and cloud-based RAG for position chat.

dljsjr /StreamObserver

Proof of concept for a streaming input, concurrent output, no-compaction inferencing implementation based on the StreamingLLM paper

SandyCompetent /exeter-academic-agent

[ARCHIVED] Learning and demo Agentic Study Assistant (Merged into SandyCompetent/chatbud)

smit-backend /laravel-stream-chat-llm

Real-time SSE event-stream chat component for Laravel Livewire and React, integrated with streaming LLM providers.

Rahul3998 /Streaming_AI_Reponse_and_TTS

Real-time LLM streaming with local CPU-based Piper TTS, sentence buffering, text cleaning, and smooth FFmpeg audio processing.

Alpha-Park /genpark-kv-cache-attention-sink-eviction-skill

GenPark AI Agent Skill - Streaming attention sink preserver and FIFO sliding-window KV cache eviction manager for infinite-context agent loops.