NVIDIA's reference Dev_ID list has seen the addition of a new "Skinny Joe" GPU which could be an AI chip designed for China with a 700W TDP.
NVIDIA's Reference DEV_ID Listing Mentions "Skinny Joe" SKU, Featuring 700W TDP & For The AI Segment
Team Green has been recently quite aggressive, when it comes to catering to Chinese markets for their AI demands, despite facing setbacks from the US Government. Just recently, the company has released the GeForce RTX 4090D, which has gained official support in the GeForce Now drivers but things don't look to stop just yet. StefanG3D, who has maintained the list of NVIDIA's reference DEV_IDS listings, has spotted the company mentioned an unknown GPU variant, most likely for the Chinese markets.
Added/updated support for
- NVIDIA_DEV.15FA = "NVIDIA DGX Station / PH402 SKU 200"
- NVIDIA_DEV.15FB = "NVIDIA GP100 SKU 200"
- NVIDIA_DEV.15FF = "NVIDIA GP100 SKU 15ff"
- NVIDIA_DEV.1DBD = "NVIDIA Tesla GV100 DGX1-V"
- NVIDIA_DEV.2342 = "NVIDIA GH200 120GB / 480GB" ; 900W TDP
- NVIDIA_DEV.2345 = "NVIDIA GH100-88K-A1" ; 700W TDP
- NVIDIA_DEV.237F = "NVIDIA Skinny Joe" ; 700W TDP
- NVIDIA_DEV.2685 = "NVIDIA GeForce RTX 4090 D"
- NVIDIA_DEV.26B7 = "NVIDIA L20" ; 275W TDP
Now, this is the first time we have seen this codename surface, but "Skinny Joe" is assigned to an AI accelerator, not only because of the 700W TDP that it comes with, but the complete listing does mention SKUs targeted towards the data center segment. NVIDIA doesn't look to stop just yet, as it might be that the company is planning for additional GPUs for the Chinese markets, but this is just a rumor for now. However, the codename does sound interesting though, I wonder where it came from.
Just recently, Team Green has initiated mass production of its Chinese-specific H20 AI accelerator, and with the "ease" in the US's stance on trade with China, NVIDIA might capitalize on it through new SKUs for the market.
News Source: Harukaze5719
About the author: Muhammad Zuhair is a hardware and technology reporter for Wccftech, specializing in the semiconductor industry and the complex interplay between technology, manufacturing, and geopolitics. His coverage focuses on the corporate strategies and technological roadmaps of industry giants like TSMC, NVIDIA, Samsung, and Intel. Zuhair's expertise lies in deconstructing complex topics such as fabrication nodes (e.g., 2nm process), the economic impact of policies like the CHIPS Act, and the strategic development of AI infrastructure from NVIDIA, AMD and Intel.
Follow Wccftech on Google to get more of our news coverage in your feeds.
