BlockBeats news, on January 31, according to Nvidia's website (NVDA.O), DeepSeek R1 671b has been released as a preview version of Nvidia NIM microservice on build.nvidia.com. DeepSeek R1 NIM microservice can process up to 3,872 tokens per second on a single Nvidia HGX H200 system. Developers can test and experiment with the API, and it is expected that the API will soon be released as part of Nvidia's AI Enterprise software platform in the form of downloadable NIM microservices. (Jinshi)
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
NVIDIA: DeepSeek R1 is now officially launched on the NVIDIA NIM platform
BlockBeats news, on January 31, according to Nvidia's website (NVDA.O), DeepSeek R1 671b has been released as a preview version of Nvidia NIM microservice on build.nvidia.com. DeepSeek R1 NIM microservice can process up to 3,872 tokens per second on a single Nvidia HGX H200 system. Developers can test and experiment with the API, and it is expected that the API will soon be released as part of Nvidia's AI Enterprise software platform in the form of downloadable NIM microservices. (Jinshi)