Blogsby GlyphIdle GPUs and runaway token bills: the real economics of production AI
Recap of the TeraSky x Spectro Cloud webinar on GPU utilization, tokenomics and inference tuning, with advice from Scott Rosenberg and Pedro Oliveira.
6 of 800 posts
Fri Sep 252 posts
AI ROI and token economics in financial services: NYC panel recap
Recap of the AI ROI + token economics panel at AI for Financial Services NYC, with Tenry Fu (Spectro Cloud), American Express, Silicon Data and Data Maverick.
Wed Sep 231 post
41 billion tokens later: dogfooding local inference routing
85 engineers, 41 billion tokens, 97.5% served locally and Claude bills 46% lower: what we learned dogfooding PaletteAI Inference Launchpad for a month.
Tue Sep 221 post
Connect Amazon Bedrock to PaletteAI Inference Launchpad
Step-by-step demo: register Amazon Bedrock as an external inference endpoint in PaletteAI Inference Launchpad, scope egress to one client and route an alias to a hosted model.
Mon Sep 212 posts
The control plane for hybrid AI infrastructure (part 2)
Tenry Fu on what a control plane for hybrid AI infrastructure does, why placement, economics and control are the themes that endure, and how to build a hybrid AI strategy.
What is hybrid AI? The seven-stop spectrum (part 1)
Spectro Cloud CEO Tenry Fu argues enterprise AI will be hybrid by default: what hybrid AI means, the seven stops inference can land on, and the forces driving it.