Open weights are step one. Making them easy to serve is step two. H3 now has Day 0 support in @vllm_project's vLLM-Omni, complete with an OpenAI-compatible video endpoint.
Huge thanks to the vLLM team for bringing H3 into the open inference stack. ⚡
#MiniMaxH3 #OpenWeights https://t.co/01dKD8PngX
An open-weights video model that serves through vLLM with an OpenAI-compatible endpoint can be run on your own hardware and dropped into existing client code without a bespoke integration.
