OpenAI Build Week

A new scheduling technique called TurboPrefill achieves up to 3.27× prefill speedup in llama.cpp by pipelining prompt microbatches across multiple GPUs, reducing inter-GPU communication bottlenecks. D…

Al-Munaa, a developer tool for agent safety developed during OpenAI Build Week, wraps agent workflows with input scanning, memory scanning, an action gate, output verification, and a Threat Antibody P…