#inference optimization
2 articles
Latest
Research
PExA Agent Balances Speed and Accuracy in Text-to-SQL
New method parallelizes SQL generation to resolve the latency-performance tradeoff in LLM-based database queries.
16 days ago4 min read
Tools
Google's TurboQuant Slashes LLM Memory Usage by 6x
New compression algorithm maintains output quality while dramatically reducing computational demands.
about 2 months ago3 min read