←Search results

Search “NVIDIA”

By relevance · Total 2038 results Clear search

Tuesday

  1. The Elec

    AMD: Real-time control and reliability are the key to physical AI

    AMD executive Salil Raje proposed that performance evaluation for physical AI should shift from raw compute power to real-time control and system-level reliability. AMD builds heterogeneous architectures with Kria AI SOM, Versal, Zynq, and Spartan FPGAs; in third-party tests, Kria AI SOM achieved inference times under 0.1 seconds and supported 8,000 control decisions per second; in open navigation benchmarks, the Ryzen AI Embedded configuration delivered control-timing reliability up to 3.4 times that of Nvidia Jetson T5000, with 1.6 times more available compute headroom.

    should shift from raw compute power to real-time control and system-level reliability. AMD builds heterogeneous architectures with Kria AI SOM, Versal, Zynq, and Spartan FPGAs; in third-party tests, Kria AI SOM achieved inference times under 0.1 seconds and supported 8,000 control decisions per second; in open navigation benchmarks, the Ryzen AI Embedded configuration delivered control-timing reliability up to 3.4 times that of Nvidia Jetson T5000, with 1.6 times more available compute headroom.

    Matched fieldsSummary、Body

    #hot-signal#English text is being prepared.#Reasoning#English text is being prepared.
  2. Shao MengSelected

    DeepSeek Open-Sources High-Performance Inference Framework DeepInfer

    DeepSeek has open-sourced DeepInfer, the high-performance inference framework supporting its online services, under the Apache 2.0 license. This release focuses on offline inference, is built primarily on vLLM, and draws on SGLang and TensorRT-LLM. It integrates previously separately open-sourced kernels such as FlashMLA, DeepGEMM, DeepEP, and EPLB into a complete engine, filling in system layers such as scheduling, parallelism, and speculative decoding, while supporting NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs. The original article also breaks down designs including DSpark speculative decoding, YoCo SWA bounded replay, asynchronous scheduling, batch-invariant deterministic inference, and regex/JSON schema/EBNF structured output.

    -LLM. It integrates previously separately open-sourced kernels such as FlashMLA, DeepGEMM, DeepEP, and EPLB into a complete engine, filling in system layers such as scheduling, parallelism, and speculative decoding, while supporting NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs. The original article also breaks down designs including DSpark speculative decoding, YoCo SWA bounded replay, asynchronous scheduling, batch-invariant deterministic inference, and regex/JSON schema/EBNF structured output.

    Matched fieldsSummary、Body

    #hot-signal#English text is being prepared.#Reasoning#English text is being prepared.
  3. Rohan Paul

    Anthropic in talks for a second $45 billion compute deal with Nscale, West Virginia reservation doubles to 920 MW

    Anthropic is in talks with Nscale for a second $45 billion compute agreement that would double its West Virginia reservation to 920 MW, adding another 460 MW building at the Monarch Compute Campus running Nvidia's Vera Rubin chips; Anthropic also holds a right of first refusal on the campus's expected third building. The first contract was signed in August, a six-year 460 MW lease with delivery starting at the end of 2027, averaging about $7.5 billion a year, or roughly $16.3 million per MW. Nscale's IPO filing lists the agreement with Anthropic at a value of up to about $44.6 billion, and the value of the second deal depends on whether the first Monarch building and its Vera Rubin racks can be powered on schedule by the end of 2027.

    h Nscale for a second $45 billion compute agreement that would double its West Virginia reservation to 920 MW, adding another 460 MW building at the Monarch Compute Campus running Nvidia's Vera Rubin chips; Anthropic also holds a right of first refusal on the campus's expected third building. The first contract was signed in August, a six-year 460 MW lease with delivery starting at the end of 2027, averaging about $7.5 billion a year, or roughly $16.3 million per MW. Nscale's IPO filing lists th

    Matched fieldsSummary、Body

    #ai-news#Industry news#Anthropic#English text is being prepared.
  9. AWS Machine Learning

    Amazon SageMaker JumpStart 2026 Progress Review

    From January to September 2026, Amazon SageMaker JumpStart added more than 100 models from 30 providers, of which Alibaba (Qwen) contributed 29, NVIDIA 17, Mistral 7, Google 6 Gemma 4 variants, IBM 4, and Cohere 4. The new models cover multimodal, speech, image, and video generation, and introduce quantized and compact models such as GLM-5.2 FP8 and JetBrains Mellum2-12B to reduce inference costs.

    Matched fieldsSummary、Body

    #lab#Product updates#English text is being prepared.#English text is being prepared.
  10. Unite.AISelected

    Inception releases flagship diffusion large model Mercury 3

    Inception released the diffusion-architecture large model Mercury 3 on October 19, 2026, claiming it surpasses GPT-6 Luna and Claude Haiku 5.5 on multiple benchmarks, reaches a speed of 1068 tokens/s on NVIDIA GPUs, and increases the context window from 260,000 in Mercury 2.5 to 1 million tokens. The launch price is $0.10 per million input tokens and $0.35 for output, with regular pricing at $0.20 and $0.70, and cached input at $0.02. Mercury 3 can be accessed via the Inception API, OpenRouter, Baseten, and Vercel, and is compatible with the OpenAI API; Mercury 2 and 2.5 are no longer available to new users, and existing customers can use them until November 15, 2026.

    diffusion-architecture large model Mercury 3 on October 19, 2026, claiming it surpasses GPT-6 Luna and Claude Haiku 5.5 on multiple benchmarks, reaches a speed of 1068 tokens/s on NVIDIA GPUs, and increases the context window from 260,000 in Mercury 2.5 to 1 million tokens. The launch price is $0.10 per million input tokens and $0.35 for output, with regular pricing at $0.20 and $0.70, and cached input at $0.02. Mercury 3 can be accessed via the Inception API, OpenRouter, Baseten, and Vercel, an

    Matched fieldsSummary、Body

    #hot-signal#Model releases#Reasoning#Agents
  11. Unite.AI

    Meta Details Prometheus Supercomputer: Has Trained Muse Models, Plans to Scale to About 1 Million GPUs

    Meta's engineering team has published technical details of the Prometheus supercomputer, confirming that the first phase has trained the Muse family of foundation models (including Muse Wonder) and that it plans to scale the system to about 1 million GPUs. The cluster is located in New Albany, Ohio, currently consists of hundreds of thousands of GPUs, and runs as a single machine; Muse Wonder achieved pretraining goodput above 85% and reinforcement learning above 90%. Meta also disclosed two platforms—Catalina based on NVIDIA GB200 NVL72 and Clemente based on GB300 NVL72—as well as the upcoming Vera Rubin NVL72 platform.

    ined the Muse family of foundation models (including Muse Wonder) and that it plans to scale the system to about 1 million GPUs. The cluster is located in New Albany, Ohio, currently consists of hundreds of thousands of GPUs, and runs as a single machine; Muse Wonder achieved pretraining goodput above 85% and reinforcement learning above 90%. Meta also disclosed two platforms—Catalina based on NVIDIA GB200 NVL72 and Clemente based on GB300 NVL72—as well as the upcoming Vera Rubin NVL72 platform.

    Matched fieldsSummary、Body

    #hot-signal#Industry news#English text is being prepared.#English text is being prepared.

Monday

  2. Rohan Paul

    Nebius commits $10 million to support European AI developers

    Nebius's AI Builder Program will expand to Europe, offering a total of $10 million in support spanning compute grants, capital, and community programs. The compute grants target areas such as open models, coding agents, post-training, and evals; in addition, the program offers connections with European VCs such as Accel, as well as hackathons and demo days co-hosted with communities such as NVIDIA and AI Tinkerers.

    Matched fieldsSummary、Body

    #ai-news#Industry news#Open-source ecosystem#English text is being prepared.
  4. TechCrunch AI

    Laplace Intelligence conducts pre-deployment red team testing for robots and autonomous vehicles

    Laplace Intelligence, incubated at the University of Michigan, is building automated red team testing for robots and physical AI. It uses high-fidelity simulation environments post-trained on Nvidia Cosmos plus AI agents to automatically design corner cases, finding and fixing problems before deployment. The company has already generated revenue and is slightly profitable; its customers include autonomous trucking company Bot Auto and a major Japanese automaker, and it is running a free smart city pilot with Nvidia and T-Mobile in San Jose, California.

    lligence, incubated at the University of Michigan, is building automated red team testing for robots and physical AI. It uses high-fidelity simulation environments post-trained on Nvidia Cosmos plus AI agents to automatically design corner cases, finding and fixing problems before deployment. The company has already generated revenue and is slightly profitable; its customers include autonomous trucking company Bot Auto and a major Japanese automaker, and it is running a free smart city pilot wit

    Matched fieldsSummary

    #tech-media#Industry news#Safety / alignment#Embodied AI