)
Mastering Multitasking: Advanced Strategies for LLM Efficiency
Dec 11, 2024
Next Generation Stage
Next Generation Stage
- Optimize LLMs on single GPUs by exploring best practices for running large language models efficiently on limited hardware
- Learn how to orchestrate solutions for complex generative use cases
- Discuss the pros and cons of fine-tuning a single LLM vs Chain-of-thoughts vs Agentic Workflow for multitasking across various tasks
- Examine additional factors that influence the quality of LLM outputs, including data quality, model architecture among others
Session Type
Keynote
Content Focus
Technical
){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
)
.svg){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
)
)
)
){kind=logo}
){kind=logo}
)
)
){kind=logo}
.jpg/fit-in/500x500/filters:no_upscale())
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
.jpg/fit-in/500x500/filters:no_upscale())
){kind=logo}
){kind=logo}
)
.png/fit-in/500x500/filters:no_upscale()){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
){kind=logo}
)
)
)
){kind=logo}
){kind=logo}
)
){kind=logo}