{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiffmnxjhtstbytrikoqiddehyjsgvkt2zg7d6fgaeqq6ofclr4mri",
"uri": "at://did:plc:gptjj5dl4jidf7yvcx4gexxy/app.bsky.feed.post/3mh7aw5qzhnh2"
},
"path": "/threads/nvidia-groq-3-lpu-and-groq-lpx-racks-join-rubin-platform-at-gtc-%E2%80%94-sram-packed-accelerator-boosts-every-layer-of-the-ai-model-on-every-token.3894104/",
"publishedAt": "2026-03-16T19:35:02.000Z",
"site": "https://forums.tomshardware.com",
"tags": [
"News Comments",
"Nvidia Groq 3 LPU and Groq LPX racks join Rubin platform at GTC — SRAM-packed accelerator boosts'every layer of the AI model on every token : Read more"
],
"textContent": "At GTC 2026, Nvidia revealed the Groq 3 accelerator and Groq LPX rack as part of the Vera Rubin platform. These SRAM-packed, inference-focused chips deliver large amounts of memory bandwidth to help Rubin deliver low-latency interactions with AI models spanning trillions of parameters and million-token contexts.\n\n**Nvidia Groq 3 LPU and Groq LPX racks join Rubin platform at GTC — SRAM-packed accelerator boosts'every layer of the AI model on every token : Read more **",
"title": "Nvidia Groq 3 LPU and Groq LPX racks join Rubin platform at GTC — SRAM-packed accelerator boosts 'every layer of the AI model on every token"
}