搜索“NVIDIA”

beer, too. It is not clear what models Meta Platforms might load on its infrastructure, but clearly it will do whatever key customers want. If it does have excess capacity on its Nvidia and AMD GPU clusters, it can pretty much run any model its customers want it to run. That will not necessarily be the case on its homegrown MTIA accelerators, which have a fairly aggressive roadmap between now and the end of next year. The Bloomberg report also says that Meta Platforms is considering offering mo

匹配字段正文

于前代产品的网络性能，但能力肯定是相关的。若一切不变，这指向一种可能性：美国政府认定某个特定的中国开源权重模型对公众不安全。这里还有许多其他潜在情景，但清楚的是，我们在梳理这些情景、准备我们的基础设施以及向社会传递信息方面还有大量工作要做。 要为一个能力日益强大的开源模型世界构想并向决策者传达管理之道，需要远不止我一个人。2 我们未来还有多年的 AI 进步，Nvidia 的下一代芯片已投产，算法进步源源不断。对开源模型倡导者来说，这感觉是一条狭窄的道路，但我们需要弄清楚如何让它们可行，这样性能的巨大飞跃才不会只流向闭源模型。 我完全理解，想象一个可公开获取的 Mythos 级模型为何令人恐惧，但如果开源模型现在被禁，而只有闭源模型在两年内于一两家公司手中变好 10 倍或 100 倍，我认为我们手上的问题会更大。 一直让我印象深刻的是中国实验室发布模型的速度。我从多个实验室听说，模型训练完成后公开上传权重到 HuggingFace 的时间可以用小时而非天来衡量。这一点至少有所放缓，因为他们现在需要准备将模型服务于更广泛的推理市场。 需要更多讨论的一点是，即便是闭源模型，例如 Mythos

匹配字段正文

ks It won't kill you, or humanity, to get off the AI upgrade treadmill New models arrive so fast, we already have more new tech than it's possible to understand in a career Cisco, Nvidia team up to build fatter, faster pluggable If you thought 1.6 Tbps was fast, just wait, Cisco's USFP targets 12.8 Tbps in a single optical pluggable TOP STORIES Anthropic asks users to stop being mean to Claude; '123456' password linked to Denmark data breach affecting 8.8M people; Microsoft and Anthropic play in

匹配字段正文

on up. In March 2025, our kernels team had grown to about 15 people: a mix of ML researchers seeking systems challenges and GPU veterans moving into AI. We'd just gotten access to NVIDIA's new Blackwell GPUs, the latest generation of hardware with fundamentally different capabilities from their predecessors. The challenge was specific: NVIDIA's teams had spent a year developing optimized kernels for Blackwell, with dozens of engineers and intimate knowledge of the hardware. We had a week. We nee

匹配字段正文

ce sheets (some of which is also the famous ‘circular revenue’). You can watch plenty of three-hour podcasts discussing all of this, and plenty of people have opinions about TPUs, Nvidia’s product lead, and Oracle’s strategy of borrowing against a declining but cash-generative legacy business to burn its way into the new thing, but how much should the rest of us care? Is this a path to a competitive advantage, or just a seat at the table? We don’t really know what AI infrastructure costs will lo

匹配字段正文

of an ecosystem of specialised models built on open-source than most people realise. And the ceiling is rising every quarter. So I don’t think open-source needs to wait out the frontier labs. I think it just has to wait out the gap. References The Michael Scott Paper Company. The Office; Nvidia GTC 2025: Built for Reasoning. SemiAnalysis (2025); Dario Amodei. Dwarkesh Podcast; Cournot competition. Wikipedia; Khatri et al.. The Art of Scaling Reinforcement Learning Compute for LLMs. arXiv (2025)

匹配字段正文

geting the attention mechanism to scale linearly with sequence length. Examples of this include the Gated DeltaNets in Qwen3-Next and Kimi Linear, as well as the Mamba-2 layers in NVIDIA’s Nemotron 3. Anyways, I don’t want to go into too much detail here because I have a whole 13k-word and recently-updated article dedicated to these architectures here if you want to learn more: The Big LLM Architecture Comparison. My prediction is that we will keep building, and with the transformer architecture

匹配字段正文

ready for the GPUs to be moved in to create the largest single datacenter in the world, yet again. xAI has to raise the capital for those GPUs, but they have the allocations from Nvidia to have it fully training large scale models early next year. Elon came up with a new genius trick to beat rivals at time-to-market. Colossus 2 will be an even more impressive achievement than xAI’s first cluster. Let’s dig in. The first half of this report will dig into the Colossus 2 prowess. The second half w

匹配字段正文

I race. These moves have led to backlash, including with China cutting rare earth minerals and magnets off from the US. Secretary of Commerce Howard Lutnick says the resumption of Nvidia GPU sales to China were required to restart China's shipments of their linchpin supply chain materials. But constraints have also led to adaptation, and Chinese companies have adapted. High batch sizes and disaggregated serving are but two examples. Despite advances, in the case of DeepSeek, most of their tokens

匹配字段正文

its, making cost, efficiency, power, performance per TCO, and reliability central to the discussion on effective training. The Hopper vs Blackwell comparisons are not as simple as Nvidia would have you believe. In this report, we will start by present the results of benchmark runs across over 2,000 H100 GPUs, analyzing data on model flops utilization (MFU), total cost of ownership (TCO) and cost per training 1M tokens. We will also discuss energy use, examining the energy in utility Joules consu

匹配字段正文

future of HBM. We will cover the revolutionary change coming to HBM4 with custom base dies for HBM, what various different accelerators are doing with custom HBM including OpenAI, Nvidia, and AMD, the shoreline area problem, memory controller offload, repeater PHYs, LPDDR + HBM combos, and various beachfront expansion techniques. We will also discuss SRAM tags, compute under memory, supply chain implications, and Samsung. A Brief Overview of HBM As AI models grow in complexity, AI systems requir

匹配字段正文

oint in Level 2. Hardware Boosts Lastly, developments in hardware have enabled these robots’ autonomy by equipping them with adequate means. Onboard compute advancements, like the Nvidia Jetson, has enabled robots to ingest and process significantly more data. Multiple sensors, cameras, and LiDARs can now all be used to generate high-quality, real-time perception data, enabling rapid adaptation to the inherent randomness of the environment. Lastly, high efficiency actuators and enhanced batterie

匹配字段正文

nodes, resulting in many more collectives (NCCL) running across the scale-out network (InfiniBand or RoCE) instead of the scale-up network (NVLink). This is a major motivation for NVIDIA’s NVL72 design, where the scale-up network expands beyond standard 8-way servers. Expert choice routing, introduced by Google in 2022, flips the logic: experts choose the top-N tokens. Taking the same T x E tensor produced by the router, in expert choice routing a topN softmax is run on the T dimension which pro

匹配字段正文

lications (e.g., powering Amazon Rufus and LinkedIn AI features). Our bi-monthly meetups have become strategic gatherings for partnerships with industry leaders like IBM, AWS, and NVIDIA, marking our progress toward becoming the universal serving solution for the open-source AI ecosystem. Read on for more details about vLLM's 2024 achievements and 2025 roadmap! This blog is based on the 16th session of the bi-weekly vLLM Office Hours. Watch the recording here. Community Contributions and Growth

匹配字段正文