8 | @hark_labs
Scaling Multimodal Data Curation with SGLang and KubeRay at Hark
Kai-Hsun Chen & Cindy Zhang on multimodal data curation, GPU orchestration, and faster inference-worker startup.
Hark details multimodal data curation with SGLang and KubeRay
AIHark engineers Kai-Hsun Chen and Cindy Zhang describe how they scale multimodal data curation with SGLang and KubeRay. The post covers GPU orchestration and faster inference-worker startup.
@lmsysorg
Part of a thread · earlier post