papers-of-the-month/an-llm-feast/

[giscus[bot]]

papers-of-the-month/an-llm-feast/

This month we’ve got an all-LLM menu of papers for you, with summaries of four great works exploring many different aspects of crafting systems for LLM training and inference.

https://graphcore-research.github.io/papers-of-the-month/an-llm-feast/

[da462]

As the field is moving more towards scaling inference compute instead of model size and nvidia has less of an edge here is graphcore working on making chips that are efficient for inference?