Multi-LoRA serving: the single translator with a thousand glossaries — shared base, thousands of concurrent adapters and the SGMV kernelMay 30, 2026
Modern alignment: DPO, KTO, ORPO and SimPO — the sommelier who learns without a reward modelMay 27, 2026
MLOps specific to LLMs in 2026: the landscape of three modalities, six stages and ten tools that make them workMay 21, 2026