OngoingOnline · Tech · advanced · ai, optimization, inference
A free global competition for developers to optimize AI model performance and inference efficiency using the FlagOS stack and SGLang framework. Participants can compete individually or in teams of up to five to solve low-level operator and throughput challenges.
OngoingOnline · Tech · advanced · ai, llm, optimization
A global team-based competition to optimize SGLang AI inference kernels for multiple chips using Triton or Triton-TLE. Participants tackle over 200 performance challenges to improve LLM throughput and latency, competing for awards based on optimization breakthroughs and extreme p