High-Performance Inference for Open LLMs with Modal, Qwen and SGLang

​When do open models and inference engines beat proprietary solutions?

​Join Modal, Qwen, and SGLang for an evening optimizing performance and cost for LLM inference. Our speakers will cover:

• ​The Cold Start Issue — how can AI infrastructure enable seamless AI experiences, right from the start?

• ​​Accelerating Open Models — how do inference engines work with model developers to achieve benchmarking goals?

• ​Choosing the Best Model — how should developers choose the most effective model for their use case?

​​With:

• ​​Charles Frye, GPU Enjoyer & Developer Advocate at Modal

• ​Qiaolin Yu, Performance Optimization at SGLang

• ​Nishant Agrawal, Senior Solutions Architect at Alibaba Cloud

​​​Agenda

​We're excited to bring together founders, AI engineers, and ML systems researchers for an evening with:

• ​​​Demos & Lightning Talks

• ​​​​Community, Pizza, Drinks

​​Your hosts,

​​Modal, Qwen & SGLang