Optimizing LLM Inference with NVIDIA KVPress Learn how NVIDIA KVPress optimizes inference for long-context language models, improving efficiency and reducing memory usage.
NVIDIA Releases AITune: Open-Source Toolkit for Optimizing PyTorch Models NVIDIA has released AITune, an open-source toolkit that automatically optimizes PyTorch model performance, simplifying production deployment.
VimRAG: Alibaba Tongyi Lab's New Multimodal RAG Framework Alibaba's Tongyi Lab has introduced VimRAG, a multimodal RAG framework that uses a memory graph to navigate complex visual contexts.
Knowledge Distillation: Optimizing Ensemble Models into a Single AI Model Learn how knowledge distillation turns complex ensemble models into a single efficient, deployable AI model.
Glossary of Common Artificial Intelligence Terms A comprehensive glossary of the most common artificial intelligence terms, from LLMs to hallucinations.
TriAttention: Optimizing the KV Cache in LLMs TriAttention, a new KV cache compression technique, improves the efficiency of large language models by reducing memory use and increasing processing speed.
MiniMax M2.7: The 230-Billion-Parameter Open-Source AI Model with Self-Evolution MiniMax has released M2.7, a 230-billion-parameter AI model with self-evolution capabilities, available on Hugging Face.