NVIDIA Rubin

Headlines · 6

1. 3d
   King Slide founder becomes Taiwan's richest as AI server rails surge

   TMTPost reported that the 2026 Hurun Rich List placed King Slide founder and chairman Lin Congji at the top of Taiwan's wealthy ranking, with a reported net worth of RMB 135 billion. King Slide reportedly holds about 80% of the global high-end server rail market and recorded an 87.42% gross margin in Q2 2026, aided by demand for AI servers. The company is building a plant in Houston and developing rails for NVIDIA's Blackwell and Rubin platforms.

   钛媒体 · 🔥 0
2. 5d
   TSMC reportedly weighs 10%–20% CoWoS price increase amid AI demand

   Taiwanese media cited supply-chain sources saying TSMC is considering raising CoWoS advanced-packaging prices by 10%–20%, while other foundries and packaging firms are evaluating similar adjustments. TSMC has not confirmed the reported increase. AI accelerator demand has expanded CoWoS orders beyond GPUs to server CPUs and custom ASICs, tightening packaging and testing capacity as relevant equipment lead times reportedly lengthened from three-to-six months to six-to-eight months.

   cnBeta · 🔥 0
3. Oct 23
   vLLM Adds Day-0 Support for MiniMax-M3.1-Flash

   vLLM Blog reports day-0 support for MiniMax-M3.1-Flash on NVIDIA Blackwell GPUs, NVIDIA Rubin GPUs with dedicated kernels, and AMD MI350-series GPUs. Prebuilt NVIDIA and AMD images are available. The implementation uses MiniMax Sparse Attention, an NVFP4 KV cache, NVFP4-quantized MoE weights and a DSpark drafter. vLLM reports gains in kernel and serving performance, including optimized agentic serving on GB300, Rubin and MI355X hardware. It also reports day-0 end-to-end reinforcement-learning support with veRL, FSDP2 and LoRA, demonstrated on 16 GB300 GPUs.

   vLLM Blog · 🔥 0
4. Oct 17
   Morgan Stanley lifts Q4 DRAM, NAND contract price forecasts; compute still top AI pick

   A Morgan Stanley report raised its memory contract-price forecasts: Q4 2026 DRAM contract prices are now seen up 10–15% quarter over quarter (from +3–8%), with PC DRAM at +13–18% and server DRAM at +10–15%, while NAND moves to +15–20% from +0–5% and enterprise SSDs reach +23–28%. The bank forecasts 2027 HBM average selling prices up 121% year over year, with HBM4 at US$3–5 per Gb and HBM4e above US$5, but says Nvidia's Rubin ramp is behind schedule, with 2026 VR200 NVL72 rack shipments estimated below 10,000 units versus an original target of about 15,000. It keeps its AI supply-chain priority of compute first, networking second and selective memory allocation, and projects DRAM capex of US$98 billion in 2026 (+82%) rising to US$150–160 billion in 2027.

   科技新报 · 🔥 0
5. Oct 12
   Frore unveils diamond-infused coldplates for 2,300W Nvidia Rubin, claims up to 22C drop

   Frore Systems introduced LiquidJet Diamond, a bespoke liquid-cooling coldplate series that adds diamond-wafer heat spreaders at the bottom of the coldplate to target hotspots on next-generation AI accelerators such as Nvidia's Rubin and AMD's Instinct MI400 and MI500. The company claims the design handles hotspot power densities up to 770 W/cm², lowers GPU temperatures by 16–22C versus conventional coldplates and improves AI token throughput per watt by 30%–35%, though those figures come from its own models and it has not disclosed how the diamond wafers are manufactured or integrated. Frore plans to demonstrate the technology at the OCP Global Summit on October 12–16, showing cooling for Nvidia's 2,300W Rubin, but has not said whether the demo uses production GPUs or a thermal test vehicle.

   Tom’s Hardware · 🔥 0
6. Oct 12
   Microsoft unveils Maia 300 inference accelerator for 2027 deployment

   Microsoft unveiled Maia 300, its third-generation in-house AI accelerator, as an inference-first system intended for multi-gigawatt deployment from 2027. Each accelerator has eight HBM4 stacks totaling 288 GB, 18 TB/s of bandwidth and a 950 W thermal design power, while a 96-accelerator rack is rated at 167 kW. Microsoft claims 40% more tokens per megawatt than leading GPU systems and up to seven times the rack-scale token throughput of Maia 200, but independent production measurements are not available and the efficiency metric lacks a clear definition.

   The Verge AI · 🔥 0

Experience and discussion from the community

Share my NVIDIA Rubin experienceAsk about NVIDIA Rubin