Moonshot AI

Latest AI news, models and releases from Moonshot AI. ['GLM 5.2', 'GLM-5.2', 'Hermes', 'K2', 'K2.6', 'K2.7', 'K3', 'K3-mini', 'K3-MoE', 'Kimi', 'Kimi 2.6', 'Kimi-2.6', 'Kimi 3', 'Kimi 3T', 'Kimi Hosted Agent', 'Kimi k1.5', 'Kimi K1.5', 'kimi-k2', 'Kimi K2', 'kimi-k2-0711-preview', 'Kimi K2.5', 'Kimi-K2.5-1T-A32B', 'Kimi K2.6', 'Kimi K2.7', 'Kimi K2.7 Code', 'Kimi K2 Thinking', 'Kimi K3', 'Kimi-K3', 'Kimi K3.5', 'Kimi K4', 'Kimi K5', 'Kimi Linear', 'Kivine', 'Krea 2', 'Krea 2 Turbo', 'Mamba', 'Mamba-2', 'Mamba-3', 'MiniCPM-RobotManip', 'MiniCPM-RobotTrack']

Official site ↗

Models 🇨🇳

Kimi K3: What Is the Strength of the Domestic Open Model and When Will It Become Available to New Users?

Chinese company Moonshot AI has released the open-source large language model Kimi K3. The developers claim significant superiority over previous versions, but the exact timeline for granting access to new users has not yet been announced.

Moonshot AI

Moonshot Kimi (GNews)27.07 · 09:05

Hardware & Inference 🇷🇺

LLM Inference: From KV-Cache to Production Deployment

MLOps engineer from hh.ru explains the fundamentals of LLM inference on on-premises hardware. The article covers KV-cache, inference engines vLLM and SGLang, attention mechanisms evolution (MHA, GQA, MLA, DSA), and practical recommendations for choosing hardware and parallelism schemes.

vLLM

SGLang