Nvidia claims TensorRT-LLM will double the H100’s performance for running inference on leading LLMs when the open-source library arrives in NeMo in October (Dylan Martin/CRN)

Nvidia claims TensorRT-LLM will double the H100’s performance for running inference on leading LLMs when the open-source library arrives in NeMo in October (Dylan Martin/CRN)

Dylan Martin / CRN:
Nvidia claims TensorRT-LLM will double the H100’s performance for running inference on leading LLMs when the open-source library arrives in NeMo in October  —  The AI chip giant says the open-source software library, TensorRT-LLM, will double the H100’s performance for running inference …