Efficient LLM inference on Slurm clusters.
-
Updated
Jan 22, 2026 - Python
#
llm-infrastructure
Here are 13 public repositories matching this topic...
A practical, multi-layered JSON repair library for Elixir that intelligently fixes malformed JSON strings commonly produced by LLMs, legacy systems, and data pipelines.
json elixir otp functional-programming data-validation beam json-parser erlang-vm error-recovery data-quality json-validation json-repair json-fix llm-infrastructure malformed-json nshkr-ai-infra
-
Updated
Dec 29, 2025 - Elixir
PipelineLLM 是一个系统性的大语言模型（LLM）后训练学习项目，涵盖从监督微调（SFT）到偏好优化（DPO）、强化学习（RLHF/PPO/GRPO）再到持续学习（Continual Learning)的完整技术栈。
reinforcement-learning lora fine-tuning post-training continual-learning sft rlhf llm-reasoning preference-optimization llm-infrastructure llm-processing
-
Updated
Jan 16, 2026 - Python
A lightweight Bun + Express template that connects to the Testune AI API and streams chat responses in real time using Server-Sent Events (SSE)
-
Updated
Aug 26, 2025 - TypeScript
Full-featured Elixir client for the Model Context Protocol (MCP) with multi-transport support, resources, prompts, tools, and telemetry.
http elixir otp sdk beam mcp telemetry api-client sse observability jsonrpc genserver resource-management ai-agent llm prompt-engineering ai-tooling model-context-protocol llm-infrastructure nshkr-ai-sdk
-
Updated
Nov 8, 2025 - Elixir
A Compute-Agnostic, WebSocket-first protocol for AI Agents. The high-performance alternative to MCP. Runs on Serverless or stateful servers with sub-30ms latency.
agent distributed-systems serverless protocol websockets low-latency ai-agents event-driven-architecture bidirectional-streaming protocol-design agentic agent-protocol real-time-ai llm-infrastructure mcp-alternative
-
Updated
Dec 10, 2025
【非结构化数据pipeline】目标是自动化原始数据—>特定信息提取。first_example:收集任何的文档将其可视化为思维导图（进度1/3）
-
Updated
Sep 4, 2025 - Python
A production-ready, enterprise-grade Agentic RAG ingestion pipeline built with n8n, Supabase (pgvector), and AI embeddings. Implements event-driven orchestration, hybrid RAG for structured and unstructured data, vector similarity search, and multi-tenant architecture to deliver client-isolated, retrieval-ready knowledge bases.
data-engineering-pipeline multi-tenant-architecture vector-database ai-workflows pgvector ai-search-engine semantic-search-ai rag-pipeline cloud-native-architecture agentic-ai-development ai-embeddings retrieval-augmented-generation-rag n8n-automation enterprise-ai-engineering llm-infrastructure rag-backend document-intelligence-rag supabase-postgres event-driven-pipelines knowledge-ingestion
-
Updated
Jan 10, 2026 - PLpgSQL
-
Updated
Jan 23, 2026 - Go
MindScript Ledger is the temporal memory and pattern-recall layer of the MindScript ecosystem. It stores normalized prompts, logic states, patterns, and threads as a structured ledger, enabling deterministic recall and reconstruction of long-running AI interactions.
prompt-engineering llm-tools ai-memory structured-prompts llm-infrastructure minds-eye mindscript-language mindscript-ledger temporal-ledger
-
Updated
Dec 9, 2025
Enterprise-grade Sovereign AI Stack optimized for NVIDIA Blackwell (sm_120) & vLLM. Features 256K context window, 5.8k tok/s prefill, and integrated observability via Langfuse.
-
Updated
Jan 21, 2026 - Python
⚡ Streamline AI agent communication with Agent Socket, a high-performance WebSocket protocol designed for diverse computing environments.
agent distributed-systems serverless protocol low-latency ai-agents event-driven-architecture bidirectional-streaming protocol-design agentic agent-protocol real-time-ai llm-infrastructure mcp-alternative
-
Updated
Jan 23, 2026
A production-ready, enterprise-grade Agentic RAG ingestion pipeline built with n8n, Supabase (pgvector), and AI embeddings. Implements event-driven orchestration, hybrid RAG for structured and unstructured data, vector similarity search, and multi-tenant architecture to deliver client-isolated, retrieval-ready knowledge bases.
data-engineering-pipeline multi-tenant-architecture vector-database ai-workflows pgvector ai-search-engine semantic-search-ai rag-pipeline cloud-native-architecture agentic-ai-development ai-embeddings retrieval-augmented-generation-rag n8n-automation enterprise-ai-engineering llm-infrastructure rag-backend document-intelligence-rag supabase-postgres event-driven-pipelines knowledge-ingestion
-
Updated
Jan 10, 2026 - PLpgSQL
Improve this page
Add a description, image, and links to the llm-infrastructure topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-infrastructure topic, visit your repo's landing page and select "manage topics."