Every Baseten story collected by The AI Daily, 2 so far, newest first, refreshed hourly.
NVIDIA Launches AIPerf to Benchmark LLM Inference at ScaleNVIDIA launched AIPerf, a ground-up rewrite replacing GenAI-Perf, using a multiprocessed ZMQ architecture to bypass the Python GIL for accurate LLM inference benchmarking. It supports over 15 endpoint types and datasets like ShareGPT.
Base Labs launches open-weight model safety standardBaseten’s Base Labs partnered with Hugging Face and Goodfire to create safety evaluation and monitoring infrastructure for open-weight models, aiming to bake safety into training and deployment to counter risks from “abliteration.” Hugging Face lists over 6,000 abliterated models; Baseten raised $1.5B in a June Series F at a $13B valuation.
The A.I. Daily