Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)
-
Updated
Apr 13, 2025 - Python
#
llm-architecture
Here are 41 public repositories matching this topic...
An architectural persistence experiment for large language models. Claude’s Home gives an AI time, memory, and place by combining scheduled execution with a durable filesystem, allowing one continuous instance to reflect, create, and evolve across sessions.
ai-experiments human-ai-interaction ai-observability llm-architecture experimental-ai ai-persistence
-
Updated
Apr 16, 2026 - TypeScript
ai architecture agents llm llm-agent llm-architecture agentic-workflow agentic-ai ai-architecture ai-architect ai-architecture-compliance
-
Updated
Apr 19, 2026 - Python
Production-grade architecture patterns, decision frameworks, and best practices for building reliable AI agents. Framework-agnostic reference for engineers.
-
Updated
Jan 31, 2026
Jetta-Reinforcement-Learning-Hybrid-LLM-Architecture
ai artificial-neural-networks large llm largelanguagemodel llm-architecture largelanguagemodelsarachitecture
-
Updated
Sep 18, 2024
Visualize some important concepts related to LLM architectures.
transformers attention-mechanism huggingface huggingface-transformers tokenizers llm llm-inference llm-architecture
-
Updated
Oct 16, 2023 - Jupyter Notebook
The Compositional Agentic Architecture (CAA): A blueprint for building reliable, deterministic, and safe industrial AI agents.
-
Updated
Feb 3, 2026 - Python
Multi-agent, policy-driven AI system for processing sensitive enterprise documents with extraction, analysis, verification, deterministic orchestration, and full audit logging. Designed for regulated environments (banking, finance, insurance).
python openai document-analysis multi-agent-systems policy-engine audit-logging verification-layer ai-governance enterprise-ai llm-architecture agentic-ai ai-orchestration regulated-industries
-
Updated
Apr 13, 2026 - Python
A collection of Small Language Models (SLMs) built from scratch in PyTorch.
-
Updated
Sep 28, 2025 - Jupyter Notebook
Educational AI chat client: provider abstraction, token compression & state management in ~600 lines Python. Learn robust AI integration patterns.
compression reference optimization chatbot educational multi-model token reference-implementation bot-development api-abstraction chat-interface streamlit ai-assistant llm developer-education claude-ai llm-architecture token-optimization fallback-llm
-
Updated
Mar 17, 2026 - Python
The first end-to-end programming language and compiler fully developed by AI.
programming-language rust compilers accrete ai-generated ai-engineering artificial-language llm-architecture ai-solutions-architect
-
Updated
Jan 4, 2026 - Rust
Code and data for: Three Phases of Expert Routing — How Load Balance Evolves During MoE Training
deep-learning transformer moe research-paper load-balancing mixture-of-experts training-dynamics phase-transitions mean-field-games llm-architecture sparse-models expert-routing
-
Updated
Apr 5, 2026 - Python
An LVM-based Instruction Set Architecture (ISA) for context management. Modeling LLMs as Logic Processors with recursive logic trees to solve attention dilution in complex tasks. | 基于逻辑虚拟内存 (LVM) 与指令集架构 (ISA) 的 LLM 上下文协议。将模型建模为逻辑处理器，通过递归逻辑树与分层寻址，解决长程任务中的注意力稀释与智力坍缩。
state-management llm-architecture context-management logic-decoupling zenith-cascade paged-context logical-traceability
-
Updated
Mar 4, 2026
A distributed, LLM-powered microservices architecture for deterministic marketing orchestration on Google Cloud.
python bigquery microservices gcp gemini event-driven marketing-analytics fastapi streamlit bigquery-ml vertex-ai customer-intelligence llm-architecture
-
Updated
Apr 5, 2026 - Python
Technical architecture and engineering lessons from building MyMate — a persistent-memory AI desktop application for long-session performance.
-
Updated
Feb 22, 2026
HSPMN: Hybrid Sparse-Predictive Matter Network - LLM architecture optimized for Blackwell GPUs bridging O(N) and O(N^2) routing via ALF-LB
machine-learning research deep-learning pytorch artificial-intelligence neural-networks triton predictive-coding sparse-attention llm-architecture nvidia-blackwell
-
Updated
Mar 7, 2026 - Python
Production-oriented Telegram → n8n → FastAPI intake CRM with deterministic state machine and audit log
python docker integration state-machine telegram-bot workflow-automation idempotency ai-systems fastapi n8n prompt-engineering ai-workflows llm-architecture deterministic-ai
-
Updated
Jan 24, 2026 - Python
Hackable PyTorch template for decoder-only transformer architecture experiments. Llama baseline with RoPE, SwiGLU, RMSNorm. Swap components, train, compare
template deep-learning pytorch transformer llama language-model autoregressive rope pytorch-implementation llm llm-architecture swiglu
-
Updated
Jan 23, 2026 - Python
DeepHelix — The DNA-Inspired DeepSeek Architecture
-
Updated
Apr 10, 2026
Reference architecture for structured AI memory lifecycle management — from the OPHION Memory OS Protocol.
reference-architecture openai whitepaper ai-systems ophion duckies llm-architecture ai-memory memory-os codex-system
-
Updated
May 24, 2025
Improve this page
Add a description, image, and links to the llm-architecture topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-architecture topic, visit your repo's landing page and select "manage topics."