Inferact
A technology company specializing in large language model inference services. It participates in the vLLM open-source community and provides application-layer services built on efficient inference engines.
Timeline (last 90 days)
The vLLM team worked with Reflection AI and Inferact to jointly optimize the serving path, including fused kernels and DFlash.
This version was initiated on GitHub by contributor Cam Quilici, the commit carries GitHub's verified signature, and participants come from institutions such as SemiAnalysis and Inferact.
vLLM core maintainer, Inferact co-founder and CEO Simon Mo will deliver a keynote talk at PyTorchCon North America on 'Scaling Open-Source Frontier Inference Infrastructure'.
vLLM's maintenance is characterized by a multi-institution collaborative structure, including the founders of startup Inferact and the engineering team from Red Hat AI.
This meetup is co-organized by the vLLM team together with Cohere, NVIDIA AI, and Inferact.
Inferact is a company focused on the commercial deployment of LLM inference services.
Simon Mo is a core maintainer of vLLM and also serves as the CEO of Inferact.
The first vLLM Conference was co-organized by AMD and Inferact.
All Facts (5)
The vLLM team worked with Reflection AI and Inferact to jointly optimize the serving path, including fused kernels and DFlash.
50%UnverifiedThis version was initiated on GitHub by contributor Cam Quilici, the commit carries GitHub's verified signature, and participants come from institutions such as SemiAnalysis and Inferact.
50%UnverifiedvLLM's maintenance is characterized by a multi-institution collaborative structure, including the founders of startup Inferact and the engineering team from Red Hat AI.
50%UnverifiedInferact is a company focused on the commercial deployment of LLM inference services.
50%UnverifiedSimon Mo is a core maintainer of vLLM and also serves as the CEO of Inferact.
50%