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.
More from Companies & People
- Jensen Huang slams ex-Anthropic researcher's warnings as 'outlandish' as generational AI doomerism debate heats up — nptacek · 2026-09-11
- OpenArt Ad Awards: $50,000 prize pool, 15 awards for AI-made ads — MiniMax_AI · 2026-09-11
- Tencent Hunyuan Teases More AI Coming After Hy4 Preview, Official Says — TencentHunyuan · 2026-09-11
- Report: Altman tells OpenAI staff he's 'considering' pacing AGI development, possibly with other labs — ns123abc · 2026-09-11
- OpenAI employee built a feedback app with ~750k data sources to guide product decisions — simpsoka · 2026-09-11
- Gary Marcus doubles down: OpenAI's issues start at the top with Sam Altman — GaryMarcus · 2026-09-11