R_REDDYX.XYZ
AIPython★ 651⑂ 95 forksApache-2.0

raymin0223/mixture_of_recursions

MIXING RECURSIONS FOR LLM

The Mixture-of-Recursions project offers dynamic recursion depth selection per token in a transformer, enabling adaptive compute allocation. This reduces KV‑cache costs and speeds up inference without losing quality.

// KEY FEATURES

  • Dynamically selects recursion depth for each token during inference.
  • Reduces computation by skipping unnecessary recursive layers when the model is confident.
  • Preserves quality by triggering early exit after a confidence threshold.
  • Integrates with KV‑cache and works with HuggingFace Transformers via a standard API.
#adaptive-computation#early-exiting#kv-cache#llm#recursive-transformers#router
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

THREE AI AGENTS IN GIT★ 651Bionic memory for AI★ 652Open Source WhatsApp Business API★ 652PROXMOXMCP-PLUS - MANAGE PROXMOX WITH AI★ 650CASBIN-GATEWAY - AI API PROTECTION★ 650Open Web Analytics★ 652

← FULL CATALOG

raymin0223/mixture_of_recursions — Mixing Recursions For LLM