Atlas / Distribution, hosting and standards / Inferact
Inferact
AI Market Atlas · by Pro Pluribus
vLLM creators · San Francisco
The company behind vLLM, the most-used open inference engine; $150M seed at $800M, now partnering with Google TPU and AMD.
Missed in the September build; added in the October update.
What it offers
Main offerings
- Inferact Inference Platform
- Production vLLM in your own cloud or on Inferact GPUs.
- vLLM
- The open-source inference engine it maintains.
Recent news
- Inferact says it serves 7 trillion tokens a day and partners with Moonshot on Kimi †Scale metric plus a major Chinese open-model lab as partner; exact day not given.Inferact ↗
- Inferact and AMD collaborate on agent inference on AMD GPUsTakes the commercial vLLM stack beyond NVIDIA.Inferact ↗
- Google and Inferact make TPU a first-class vLLM targetBroadens open inference across accelerators.Inferact ↗
- Inferact launches with $150M to commercialize vLLMa16z and Lightspeed co-led at an $800M valuation.SiliconANGLE ↗
This map is a by-product of the work. Keeping track of what each of these actually does, and which ones are worth your time, is part of how I advise founder-led companies on AI. If you want that applied to your business, the first conversation is free.
Book a 30-minute conversation →Compiled from public sources by Pro Pluribus; updated 10 Nov 2026. General information, not advice. Company names and logos belong to their owners and are used to identify them, without affiliation or endorsement. Terms