… Deploying with SGLang Gemma 4 can also be deployed on AMD MI300X/MI325X/MI35X GPUs using SGLang, which provides high-performance serving. SGLang supports the full Gemma 4 family including dense models E2B, E4B, 31B and the MoE variant 26B-A4B . …
… For AMD, leadership in AI means more than delivering strong performance. It means showing up early, contributing to the standards that matter, and advancing a benchmarking model built on transparency, broad industry participation, and long-term trust. …
… The alliance's first chapter centers on co-developing open-source AMD ROCm™ software-native Vision Language Action VLA models and world models. …
… That requires powerful hardware, high-bandwidth unified memory, efficient parallel compute, and the architecture to run sophisticated AI models. …
… The session will explore how enterprise clients are balancing performance, scale, and efficiency across their fleets. …