LoRAX: Serve 1000s of Fine-Tuned LLMs on a Single GPU - Travis Addair, Predibase, Inc.
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by videoExplains LoRAX technology for serving multiple fine-tuned language models efficiently on single GPU. Teaches specific tool architecture and optimization technique.
Video by The Linux Foundation, played through YouTube's embedded player.
Part of Open AI + Data Forum @ OSS NA 2024, Open Source Summit North America 2024