AI Systems

The Throughput Trap: Benchmarking vLLM on OpenXLA and the Reality of Production LLM Serving featured image

The Throughput Trap: Benchmarking vLLM on OpenXLA and the Reality of Production LLM Serving

vLLM Systems · DevLab 2026, Deep Dive I was recently invited by the Google TPU team to speak at the OpenXLA Summer DevLab 2026 . This post breaks down our deep-dive evaluation of …

avatar
Rabimba Karanjai