🎬 Ollama Gemma Day Recap: SGLang at the Ollama Gemma 4 Party in Palo Alto 🍾 Last night, @ollama hosted a packed Gemma Day at the Palo Alto…

🎬 Ollama Gemma Day Recap: SGLang at the Ollama Gemma 4 Party in Palo Alto 🍾 Last night, @ollama hosted a packed Gemma Day at the Palo Alto office alongside the @GoogleDeepMind Gemma team. SGLang was invited to do a very cool demo to close out the night. 🧠 The @GoogleDeepMind team covered it all: an intro to Gemma 4 from Omar Sanseviero, a tour of the Gemmaverse from Ravin Kumar, open medical models from Fereshteh Mahvar, and Sara Smoot introduced us to a full Gemma 4 ecosystem that includes inference engines, agentic workflows, and hardware support. SGLang is proudly listed as one of the official custom inference implementations in the Gemma ecosystem! ⚡️ Our own dev, Khoa Pham (@kwafam7) closed with a super cool live demo: deploying Gemma 4 with SGLang, then using Gemma 4 itself to fix SGLang's own Gemma 4 support issues in real time! Proud to be a Day-0 partner for Gemma 4 alongside @ollama, and looking forward to more collaboration with the @GoogleDeepMind team! 🤝

Source: Ollama (X) | 2026-04-16