TOKENS & TUNING

LLM Happy Hour

Tokens & Tuning brought together AI model builders for an informal evening focused on practical technical discussions. The organizers emphasized sharp conversations, exceptional drinks, and peers who care about throughput, customization, and escaping GPU pain. With no formal presentations or staged content, the event featured designated conversation areas organized by technical topic including fine-tuning, vLLM, LLaMA-3, and compute scaling. The target audience included engineers deploying large models, AI-native founders, researchers in language/vision/multimodal domains, and infrastructure specialists dealing with GPU cost and scaling challenges.