User : pveldandi

• Created: 1689571267
• Karma: 4
• Building InferX, a GPU-native runtime that snapshots the full execution state of LLMs so you can hot-swap models like threads.

  Obsessed with inference efficiency, cold-start elimination, and agentic infra.

  Previously: enterprise software, now deep in AI infra

  Say hi on LinkedIn: https://www.linkedin.com/in/prashanth-v-98629b115/

submissions | comments