vLLM, Red Hat and NVIDIA to host open-source inference meetup in Madrid on Nov 12
vllm_project · x · 2026-11-04
The vLLM project, with Red Hat AI and NVIDIA, will host an evening meetup on open-source inference at Madrid's MOA Institute on November 12, covering vLLM, vLLM-omni, LLM Compressor, and llm-d on Kubernetes.
Agenda highlights: intro to fast open-source inference with vLLM; omni-modality model serving (text/image/audio/video) with vLLM-omni; model compression via LLM Compressor and speculative decoding with Speculators; building safe agentic systems on open source; and scaling inference from a single GPU to a full cluster with vLLM and llm-d on Kubernetes, followed by Q&A and networking.
More from Companies & People
- Anthropic: 1,900+ customers with $1M+ TTM revenue, $100K+ base up 8X in a year — Beth_Kindig · 2026-11-04
- PyTorch Day Japan 2026 agenda drops: ExecuTorch porting to IBM AIU edge accelerator — PyTorch · 2026-11-04
- Google AI division workers push execs to waive non-disparagement agreements to warn public about AI risks — EthanJPerez · 2026-11-04
- Wafer Systems founder joins Nothing to build AI-native mobile OS after two years on the vision — zack_overflow · 2026-11-04
- Fireworks AI launches Frontier Ecosystem with 60+ partners across the AI stack — sophiamyang · 2026-11-04
- Listed as a 'Future Founder' while already building his startup, dev reacts — KlausCodes · 2026-11-04