NVIDIA and Red Hat team up with vLLM on a bounty for real builds with small open models

NVIDIAAI · x · 2026-09-11

The vLLM project announced a Best Use of vLLM bounty added alongside NVIDIA and Red Hat for an upcoming event in Raleigh: participants must build something real with small open models capped at 33B parameters, serve it with vLLM, and share honest feedback. NVIDIA AI amplified the announcement.

Original post →

More from Companies & People

Companies & People channel →