R_REDDYX.XYZ
AIC++★ 2,898⑂ 403 forksMIT

mw00/project-maya

PROJECT MAYA: LOCAL LLM ENGINE

Project Maya lets you run GLM-5.3-Flash (321B MoE) locally on a single GPU or up to 16 GPUs, supporting NVIDIA and AMD on Linux and Windows. The package includes engine, server, dashboard, OpenAI- and Anthropic‑compatible API, and quantization tools.

// KEY FEATURES

  • Run GLM-5.3-Flash (321B MoE) on a single GPU with scaling up to 16 cards.
  • Cross‑platform engine: works on NVIDIA and AMD GPUs under Linux and Windows without code changes.
  • Built‑in server and dashboard provide OpenAI‑ and Anthropic‑compatible REST API for easy integration.
  • Quantization toolkit (FP8, INT4, etc.) reduces model size and speeds up inference.
#cuda#glm#glm-5#llm#llm-inference#local-llm#mixture-of-experts#moe#openai-api#quantization#rocm#self-hosted
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

FORMAL VERIFICATION OF AI AGENTS★ 2897VOICEMEM UNIVERSAL MEMORY★ 2901OPEN ONTOLOGIES AI ENGINE★ 2905DeepSeek Reasonix: Terminal AI Agent★ 2889MOSS Image 5B DiT Model★ 2887OSWorld: BENCHMARK FOR AI AGENTS★ 2911

← FULL CATALOG

mw00/project-maya — Project Maya: Local LLM Engine