#mlperf — Public Fediverse posts

https://www.europesays.com/pl/342456/ AMD w końcu dobrało się do NVIDII? MI355X przebił milion tokenów sekundę i zrobiło się naprawdę ciekawie #ai #amd #AMDInstinctMI355X #Cdna4 #CentraDanych #MLPerf #MLPerfInference60 #Nauka #NaukaITechnika #NaukaTechnika #NVIDIAB200 #NVIDIAB300 #PL #Poland #Polish #Polska #Polski #rocm #Science #ScienceAndTechnology #ScienceTechnology #Technika #Technology

🚀 NVIDIA’s new NVFP4 training recipe slashes AI model training time and cost, powering Blackwell Ultra GPUs to set new MLPerf Training records on large language models like Llama 3.1. Discover how GPU acceleration is reshaping open‑source AI development. #NVFP4 #BlackwellUltra #MLPerf #Llama3_1

🔗 https://aidailypost.com/news/nvidias-nvfp4-training-recipe-boosts-ai-speed-cuts-costs

🚀 NVIDIA’s new NVFP4 training recipe slashes AI model training time and cost, powering Blackwell Ultra GPUs to set new MLPerf Training records on large language models like Llama 3.1. Discover how GPU acceleration is reshaping open‑source AI development. #NVFP4 #BlackwellUltra #MLPerf #Llama3_1

🔗 https://aidailypost.com/news/nvidias-nvfp4-training-recipe-boosts-ai-speed-cuts-costs

🚀 NVIDIA’s new NVFP4 training recipe slashes AI model training time and cost, powering Blackwell Ultra GPUs to set new MLPerf Training records on large language models like Llama 3.1. Discover how GPU acceleration is reshaping open‑source AI development. #NVFP4 #BlackwellUltra #MLPerf #Llama3_1

🔗 https://aidailypost.com/news/nvidias-nvfp4-training-recipe-boosts-ai-speed-cuts-costs

Large language models #LLMs are growing extremely quickly, and the #hardware systems that they require can’t keep up with the pace. Each time #MLPerf introduces a new benchmark, training time increases. The data tells the story. spectrum.ieee.org/mlperf-trends

This year's #MLPerf introduced three new benchmark tests (its largest yet, its smallest yet, and a new voice-to-text model), and #Nvidia's Blackwell Ultra topped the charts on the two largest benchmarks.

MLPerf Introduces Largest and ...

💪 NVIDIA Blackwell Ultra: 5× schneller – wieso?

▶️ Erklärt NVFP4 und TTFT
▶️ Nutzt 288GB HBM3e RAM!
▶️ Trennt Kontext und Gen

#ai #ki #artificialintelligence #BlackwellUltra #Nvidia #mlperf #aiinference #tech2025

💬 LIKEN ❤️ TEILEN 🔄 LESEN 📖 FOLGEN ➕

https://kinews24.de/nvidia-blackwell-ultra-architektur-benchmark-rekorde-2025/

💪 NVIDIA Blackwell Ultra: 5× schneller – wieso?

▶️ Erklärt NVFP4 und TTFT
▶️ Nutzt 288GB HBM3e RAM!
▶️ Trennt Kontext und Gen

#ai #ki #artificialintelligence #BlackwellUltra #Nvidia #mlperf #aiinference #tech2025

💬 LIKEN ❤️ TEILEN 🔄 LESEN 📖 FOLGEN ➕

https://kinews24.de/nvidia-blackwell-ultra-architektur-benchmark-rekorde-2025/

💪 NVIDIA Blackwell Ultra: 5× schneller – wieso?

▶️ Erklärt NVFP4 und TTFT
▶️ Nutzt 288GB HBM3e RAM!
▶️ Trennt Kontext und Gen

#ai #ki #artificialintelligence #BlackwellUltra #Nvidia #mlperf #aiinference #tech2025

💬 LIKEN ❤️ TEILEN 🔄 LESEN 📖 FOLGEN ➕

https://kinews24.de/nvidia-blackwell-ultra-architektur-benchmark-rekorde-2025/

💪 NVIDIA Blackwell Ultra: 5× schneller – wieso?

▶️ Erklärt NVFP4 und TTFT
▶️ Nutzt 288GB HBM3e RAM!
▶️ Trennt Kontext und Gen

#ai #ki #artificialintelligence #BlackwellUltra #Nvidia #mlperf #aiinference #tech2025

💬 LIKEN ❤️ TEILEN 🔄 LESEN 📖 FOLGEN ➕

https://kinews24.de/nvidia-blackwell-ultra-architektur-benchmark-rekorde-2025/

💪 NVIDIA Blackwell Ultra: 5× schneller – wieso?

▶️ Erklärt NVFP4 und TTFT
▶️ Nutzt 288GB HBM3e RAM!
▶️ Trennt Kontext und Gen

#ai #ki #artificialintelligence #BlackwellUltra #Nvidia #mlperf #aiinference #tech2025

💬 LIKEN ❤️ TEILEN 🔄 LESEN 📖 FOLGEN ➕

https://kinews24.de/nvidia-blackwell-ultra-architektur-benchmark-rekorde-2025/

New #MLPerf training results are in, and #Nvidia's Blackwell GPUs continue to dominate across all six benchmarks. The computers built around the newest AMD GPU, MI325X, matched the performance of Blackwell’s predecessor on the most popular LLM fine-tuning benchmark. spectrum.ieee.org/mlperf-train...

Is Nvidia's Blackwell the Unst...

MLPerf Training 5.0: Nvidia setzt sich mit GB200 NVL72 an die Spitze https://www.computerbase.de/news/pc-systeme/mlperf-training-5-0-nvidia-setzt-sich-mit-gb200-nvl72-an-die-spitze.92964/ #Nvidia #MLPerf #Blackwell

Learning about the value of benchmarks at #AIFD6, including #MLPerf Storage and Client, from David Kanter of #MLCommons

Watch live on TechFieldDay.com!

Learning about the value of benchmarks at #AIFD6, including #MLPerf Storage and Client, from David Kanter of #MLCommons

Watch live on TechFieldDay.com!

Learning about the value of benchmarks at #AIFD6, including #MLPerf Storage and Client, from David Kanter of #MLCommons

Watch live on TechFieldDay.com!

Learning about the value of benchmarks at #AIFD6, including #MLPerf Storage and Client, from David Kanter of #MLCommons

Watch live on TechFieldDay.com!

Learning about the value of benchmarks at #AIFD6, including #MLPerf Storage and Client, from David Kanter of #MLCommons

Watch live on TechFieldDay.com!

New MLPerf Training v4.1 benchmarks are in: Nvidia’s Blackwell B200 outpaces rivals in AI benchmarks, while Google’s Trillium narrows the gap in training performance. #ai #nvidia #google #MLPerf

https://winbuzzer.com/2024/11/14/nvidia-b200-blackwell-outshines-google-trillium-tpu-in-latest-mlperf-benchmark-xcxwbn/

An actual #mlperf benchmark aligns with my predictions for single GPU performance of 4x gain. https://developer.nvidia.com/blog/nvidia-blackwell-platform-sets-new-llm-inference-records-in-mlperf-inference-v4-1/

#AMD posts first Instinct #MI300X #MLPerf #benchmark results — roughly in line with #Nvidia #H100 (But only in #Llama2 70B).
Based on data AMD shared, 8x MI300X processors only slightly slower (23,512 TOPS) than 8x H100 SXM3 (24,323 TOPS), which can probably be called 'competitive' given how well Nvidia's software stack is optimized for popular #LLM like Llama 2. AMD MI300X system is slightly faster than the H100 machine in more or less real-world server benchmarks.
https://www.tomshardware.com/tech-industry/artificial-intelligence/amd-posts-first-instinct-mi300x-mlperf-benchmark-results-roughly-in-line-with-nvidia-h100-performance

Nvidia Conquers Latest AI Tests
https://spectrum.ieee.org/mlperf-nvidia-conquers
#ycombinator #training #artificial_intelligence #large_language_models #llms #nvidia #intel #google #fine_tuning #graph_neural_networks #gpt_3 #stable_diffusion #mlperf

Nvidia Conquers Latest AI Tests
https://spectrum.ieee.org/mlperf-nvidia-conquers
#ycombinator #training #artificial_intelligence #large_language_models #llms #nvidia #intel #google #fine_tuning #graph_neural_networks #gpt_3 #stable_diffusion #mlperf

Nvidia Conquers Latest AI Tests
https://spectrum.ieee.org/mlperf-nvidia-conquers
#ycombinator #training #artificial_intelligence #large_language_models #llms #nvidia #intel #google #fine_tuning #graph_neural_networks #gpt_3 #stable_diffusion #mlperf

Nvidia Conquers Latest AI Tests
https://spectrum.ieee.org/mlperf-nvidia-conquers
#ycombinator #training #artificial_intelligence #large_language_models #llms #nvidia #intel #google #fine_tuning #graph_neural_networks #gpt_3 #stable_diffusion #mlperf

#SymLink: Stephen Foskett talks with David Kanter about MLCommons' efforts in advancing AI technology and ensuring AI safety, underlined by their benchmarking tools that help guide consumer purchasing. @GestaltIT @sfoskett #AI #AIFD4 #AIPC #AISafety #MLPerf #UtilizingAI
https://gestaltit.com/utilizing-tech/stephen/ai-pcs-renewed-focus-on-ai-safety-and-more-with-david-kanter-of-mlcommons/

Just Posted: The article "AI PCs, Renewed Focus on AI Safety, and More with David Kanter of MLCommons" summarizes a podcast episode discussing MLCommons' influence on AI innovation and safety, and its provision of transparent AI product benchmarks to aid consumer decisions. #AI #AIFD4 #AISafety #MLPerf #UtilizingAI #UtilizingTech
https://utilizingtech.com/podcast/ai-pcs-renewed-focus-on-ai-safety-and-more-with-david-kanter-of-mlcommons/?utm_source=rss&utm_medium=rss&utm_campaign=ai-pcs-renewed-focus-on-ai-safety-and-more-with-david-kanter-of-mlcommons

MLPerf training tests put Nvidia ahead, Intel close, and Google well behind
https://spectrum.ieee.org/generative-ai-training
#ycombinator #intel #mlperf #supercomputing #nvidia #generative_ai

Nvidia Still on Top in Machine Learning; Intel Chasing

The latest #MLPerf inferencing benchmarks include #Nvidia’s Grace Hopper superchip

https://spectrum.ieee.org/mlperf

Just Posted: Tom Hollingsworth's article sheds light on how the International Criminal Court, per Karim Khan's proposal, plans to extend international law to cybercriminals, alongside highlighting significant tech updates from companies like CoreWeave, Enfabrica, MGM Resorts, and Intel. @networkingnerd #AI #CyberSecurity #MLPerf #Rundown #SDC23 #Security #SFD26 #Thunderbolt5
https://gestaltit.com/rundown/tom/cybercriminals-gain-attention-from-international-criminal-courts-gestalt-it-rundown-september-13-2023/

MLPerf Inference v3.1 introduces new LLM and recommendation benchmarks https://www.artificialintelligence-news.com/2023/09/12/mlperf-inference-v3-1-new-llm-recommendation-benchmarks/ #mlperf #ai #ml #llm #news #tech #technology

#SymLink: The latest Gestalt IT Rundown highlights the impact of MLPerf 3 benchmark results, discussing performance improvements in AI training and energy efficiency, along with news on Intel's Gaudi2, Nvidia's NeMo model, the expansion of MLPerf @GestaltIT @sfoskett
https://gestaltit.com/rundown/stephen/mlperf-3-upsets-the-ai-apple-cart-gestalt-it-rundown-june-28-2023/
#AI #CentOS #Cloud #MLPerf #MLPerf3 #NetworkMonitoring #RHEL #Rundown

NVIDIA posted their #MLPerf #MachineLearning benchmarks today. Take-away:

2.5X overall speed improvements on A100 (Ampere) due to software improvements since initial release.

6.7X overall speed improvement on new H100 (Hopper) architecture vs. original A100.

Details: https://blogs.nvidia.com/blog/2022/11/09/mlperf-ai-training-hpc-hopper/

MLCommons Releases MLPerf Inference v1.0 Results with First Power Measurements

#MLPerf
#GapryBlogReadingList

https://mlcommons.org/en/news/mlperf-inference-v10/