Inferact, from the creators of vLLM, launches controllable frontier inference platform
Xianbao_QIAN · x · 2026-10-17
The team behind vLLM launched Inferact, pitched as 'frontier inference you control,' with two offerings:
- Inferact Platform: deployed in your own cloud/datacenter, keeping weights, traffic, and logs in your environment.
- Inferact Cloud: runs on their provisioned GPUs, tuned by the engineers who created and maintain vLLM.
Features include agent-tuned configurations for latency/throughput, day-0 model support with quality validation, custom kernels and trained speculators, autoscaling, metered authenticated endpoints, and per-workload observability. The site lists Google Cloud, Intel, Kimi, MiniMax, NVIDIA, and Prime Intellect among partners.
More from Infra
- Texas grid queue hits 474GW; white paper argues AI data centers should become grid resources — espricewright · 2026-10-17
- HF Transformers adds activation checkpoint offloading to CPU to free GPU memory — StasBekman · 2026-10-17
- DatologyAI claims 1000x compute-efficiency headroom from data curation, demo on Oct 27 — josh_wills · 2026-10-17
- Supabase ships MIT-licensed Middleware: write fetch logic once, run on any runtime — dshukertjr · 2026-10-17
- Dev asks for sandbox provider supporting N concurrent sandboxes with dynamically mountable disks — zeeg · 2026-10-17
- Litespark serves Nemotron 120B at 962 tokens/sec per user on just two H200 GPUs — NVIDIAAI · 2026-10-17