view article Article KV Caching Explained: Optimizing Transformer Inference Efficiency Jan 30, 2025 • 209
EXAONE-4.0 Collection EXAONE unified model series of 1.2B and 32B, integrating non-reasoning and reasoning modes. • 20 items • Updated Jul 29, 2025 • 52
Kimi-K2 Collection Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated Nov 14, 2025 • 162
Seed-X Collection A powerful open-source multilingual translation language model series, including instruction and reasoning models. • 8 items • Updated Aug 22, 2025 • 65
