FrameworksNov 17, 2026 · 06:381 source

vLLM Achieves 93.3x the Token Throughput of GB300 for DeepSeek Inference on Nvidia Rubin

From marketbrief.now

Image: marketbrief.now
AI;DR

The vLLM project reported that the DeepSeek-V4.1-Flash model running on Nvidia Vera Rubin NVL72 hardware achieves a token throughput 63.4 to 93.3 times higher than the GB300 NVL72, depending on the user rate. To optimize performance, vLLM implemented a Mooncake KV pool and sharded Engram tables over NVLink.

Read the sourceSign in to suggest

Sources

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today