vLLM claims 90x throughput on Rubin as analysts ignore software-driven gains
bookwormengr · x · 2026-11-17
The author argues stock analysts estimating AI supply/demand work too abstractly and miss how far software and architecture optimizations go within a single hardware generation. Citing the vLLM blog: with Rubin and recent optimizations, throughput can reach over 90x. He gives a hypothetical example of a model delivering 80x performance at 1/3 the size (model names are speculative, unverified), estimating up to 9000% gains at high interactivity and 300-400% at 100 tokens/sec, concluding no serious analyst models this and everything gets hand-waved with the Jevons paradox.
More from Venture
- Customer saves $9M+ by ditching API pricing and Devin for aggregated AI subscriptions — garrytan · 2026-11-17
- Michael Burry's Oracle short pays off: stock down 17.4% since August — SumitGup · 2026-11-17
- Qwen4-Max matches Opus 5.5 on Alibaba's own chart but ranks 12th independently — kimmonismus · 2026-11-17
- Tracing Nvidia's circular financing: $170B in sales, only ~$35B unsettled — tengyanAI · 2026-11-17
- Humanoid robot startup backed by Eric Trump misses payroll, may collapse after $4.6M CEO home loan — Ars Technica AI · 2026-11-17
- OpenAI says ChatGPT now handles ~20% as many searches as Google — PeterDiamandis · 2026-11-17