RAG does: retrieves relevant documents before generating to reduce hallucination

Retrieval-augmented generation

RAG enables LLMs to access new information without retraining

paged attention (vLLM) improves serving throughput

Paged attention (vLLM) improves serving throughput by reducing latency through non-contiguous KV-cache pages, enabling faster data retrieval

structured pruning removes: entire filters or attention heads, not individual weights

Structured pruning removes entire filters or attention heads, not individual weights

ring attention does: distributes long sequences across multiple devices

Ring attention distributes long sequences across multiple devices

Flashbulb memory

Flashbulb memories are vivid but not always accurate

IS (Inception Score) measures: diversity and quality of generated images

Inception Score quantifies diversity and quality of generated images