NVIDIA
El proveedor de chips y software para el cómputo de IA
El texto completo se presenta en inglés; el título y el resumen están traducidos.
QUÉ ES
NVIDIA was founded in 1993 and started with graphics processors. Its GPUs and the CUDA software stack became the de facto standard for deep-learning training, and accelerators such as the H100 and B200 are the main hardware for training large models. It also provides tools like NeMo for training and deployment.
Por qué es importante
CUDA brought general-purpose computing to the GPU, letting deep learning scale on one consistent software and hardware stack — an ecosystem that has kept it effectively irreplaceable in compute supply.
Hitos clave
- 1993
Founded
- 2007
Released CUDA
- 2022
Released the H100 accelerator
- 2024
Released the Blackwell-based B200
Productos representativos
4CUDA
2007Plataforma de programación para cómputo general en GPU NVIDIA
NeMo
2019Kit de herramientas para entrenar y personalizar modelos grandes
H100
2022Una GPU de centro de datos con arquitectura Hopper para entrenar grandes modelos
B200 (Blackwell)
2024Una GPU con arquitectura Blackwell pensada para modelos de billón de parámetros