मुख्य सामग्री पर जाएँ

B200 (Blackwell)

खरब-पैरामीटर मॉडल के लिए Blackwell आर्किटेक्चर GPU

NVIDIA हार्डवेयर बंद स्रोत

यह पृष्ठ अंग्रेज़ी में प्रस्तुत है; शीर्षक और सारांश का स्थानीयकरण किया गया है।

यह क्या है

B200 is a Blackwell-architecture data-centre GPU NVIDIA announced in March 2024. Two dies are packaged together over a high-speed interconnect for about 208 billion transistors in total, with 192GB of HBM3e memory and support for lower-precision formats such as FP4 and FP6. It uses fifth-generation NVLink at 1.8 TB/s per GPU and targets training and inference of trillion-parameter models.

यह क्यों महत्वपूर्ण है

It brought memory to 192GB and supports low-precision formats such as FP4, succeeding H100 as the main hardware for a new generation of large-model training and inference and bringing the two-die package into data-centre GPUs.

मुख्य विशिष्टताएँ

Architecture
Blackwell
Memory
192GB HBM3e
Transistors
About 208 billion
Interconnect
NVLink 1.8 TB/s
Released
2024-03

संबंधित अवधारणाएँ

समान उत्पाद