Running on CPU Upgrade Featured 3.11k The Smol Training Playbook 📚 3.11k The secrets to building world-class LLMs
Running Agents 66 KVPress Leaderboard 🥇 66 KVPress leaderboard: benchmark KV Cache compression methods
nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct Text Generation • Updated Apr 17, 2025 • 108 • 119