AI Infrastructure

Meituan has launched LongCat-2.0, a large-scale Mixture-of-Experts (MoE) language mannequin. It carries 1.6 trillion whole parameters and prompts about 48 billion per token. The mannequin targets agentic coding: code understanding, technology, and execution inside agent workflows. Two info stand out. First, LongCat-2.0 helps a local 1-million-token context window. Second, each coaching and serving ran totally…

Autoregressive giant language fashions generate textual content one token at a time. Each token waits for the one earlier than it. This serial loop leaves trendy GPUs underused and retains inference gradual. The value grows worse with lengthy Chain-of-Thought reasoning fashions. Their prolonged outputs make latency the dominant a part of era. Speculative decoding is…

Prime Intellect has launched prime-rl version 0.6.0. The framework targets reinforcement studying on trillion-parameter Mixture-of-Experts (MoE) fashions. It focuses on heavy agentic workloads, like long-horizon software-engineering duties. The analysis workforce skilled GLM-5 on SWE duties at up to 131k sequence size. Step instances stayed underneath 5 minutes. The batch measurement was 256 rollouts. The run…