English translation is being prepared.
Matched fieldsTitle、Summary、Body
←Search results
English text is being prepared.
T-Head releases Zhenwu V900 training-and-inference integrated AI chip
T-Head releases the new-generation Zhenwu V900 training-and-inference integrated AI chip. According to Jiwei.com, the chip was released on September 22 at the Hangzhou Yunqi Conference; single-chip performance reaches three times that of Zhenwu M890, can meet the training and inference needs of trillion-parameter large models, and is planned for mass production and sale in the first quarter of 2027. The report says Zhenwu V900 carries 216GB of memory, chip-to-chip interconnect bandwidth of 1200GB/s, natively supports FP8 and FP4 low-precision computing, and can form a thousand-card full-bandwidth high-speed interconnect super node with the self-developed ICN Switch interconnect chip. T-Head also for the first time announced its Yitian server CPU plan, with Yitian 720 and Yitian 730 to be launched in 2027. There are currently no subsequent development facts.
T-Head releases the new-generation Zhenwu V900 training-and-inference integrated AI chip. According to Jiwei.com, the chip was released on September 22 at the Hangzhou Yunqi Conference; single-chip performance reaches three times that of Zhenwu M890, can meet the training and inference needs of trillion-parameter large models, and is planned for mass production and sale in the first quarter of 2027. The report says Zhenwu V900 carries 216GB of memory, chip-to-chip interconnect bandwidth of 1200G
Matched fieldsTitle
Pingtouge releases Zhenwu V900, an integrated training-and-inference AI chip
T-Head releases the new-generation Zhenwu V900 training-and-inference integrated AI chip. According to Jiwei.com, the chip was released on September 22 at the Hangzhou Yunqi Conference; single-chip performance reaches three times that of Zhenwu M890, can meet the training and inference needs of trillion-parameter large models, and is planned for mass production and sale in the first quarter of 2027. The report says Zhenwu V900 carries 216GB of memory, chip-to-chip interconnect bandwidth of 1200GB/s, natively supports FP8 and FP4 low-precision computing, and can form a thousand-card full-bandwidth high-speed interconnect super node with the self-developed ICN Switch interconnect chip. T-Head also for the first time announced its Yitian server CPU plan, with Yitian 720 and Yitian 730 to be launched in 2027. There are currently no subsequent development facts.
Matched fieldsTitle
View story:T-Head releases Zhenwu V900 training-and-inference integrated AI chip
English translation is being prepared.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
Nvidia launches Open Agent Safety Platform, using BlueField-4 DPU to monitor agents
At GTC Berlin, Nvidia launched the Open Agent Safety Platform, adding hardware-level controls around the open-source runtime OpenShell; a BlueField-4 DPU works with Sentry software to independently monitor agent behavior and, when it crosses boundaries, isolate and stop it within milliseconds. OpenShell supports third-party agent frameworks such as Anthropic's Claude Code and OpenAI's Codex, and Nvidia says more than 100 organizations already use the platform's technology. Nvidia also introduced the Agent Knowledge Foundation and the Auto-Ontology library, designed to let agents access structured and unstructured data without enterprise data leaving local premises, and expanded its Nemotron 3.5 Super VL, Nemotron 3.5 Bolt 74B-A9B and Kumo series models.
At GTC Berlin, Nvidia launched the Open Agent Safety Platform, adding hardware-level controls around the open-source runtime OpenShell; a BlueField-4 DPU works with Sentry software to independently monitor agent behavior and, when it crosses boundaries, isolate and stop it within milliseconds. OpenShell supports third-party agent frameworks such as Anthropic's Claude Code and OpenAI's Codex, and Nvidia says more than 100 organizations already use the platform's technology. Nvidia also introduced
Matched fieldsBody
DeepSeek open-sources the Deepinfer inference framework, lowering the cost of self-hosted model deployment
DeepSeek has open-sourced its internal inference framework Deepinfer on GitHub, with the goal of reducing the compute and energy costs of deploying models on your own. During the inference stage, the framework distributes load more evenly across available processor cores, uses speculative decoding to speed up responses, and improves the structure of results before output; it currently supports only DeepSeek-V4.1-Flash, with more of its own models to be opened up later. On the hardware side, it requires Nvidia GPUs with the SM100 architecture or Huawei Ascend 950 NPUs, so it is not aimed at individual users.
DeepSeek has open-sourced its internal inference framework Deepinfer on GitHub, with the goal of reducing the compute and energy costs of deploying models on your own. During the inference stage, the framework distributes load more evenly across available processor cores, uses speculative decoding to speed up responses, and improves the structure of results before output; it currently supports only DeepSeek-V4.1-Flash, with more of its own models to be opened up later. On the hardware side, it r
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody