MLPerf Client v1.6 is out - runtime updates for Windows ML, llama.cpp, and Apple MLX, plus GUI improvements for faster, smoother benchmarking on Windows, Mac, and iPad.
https://bit.ly/419SyHI
#MLPerf #AIBenchmarking
Want to explore the MLPerf Inference v6.0 results yourself? Dive into our interactive dashboard - filter by benchmark, system, and scenario to see how the latest hardware stacks up. 📊
🔗 https://bit.ly/3PLbCJR
#MLPerf #MLCommons #AI #inference
Wow! Nvidia just smashed the MLPerf leaderboard with a 288‑GPU B300 cluster, leaving AMD & Intel scrambling. See how this beast redefines hardware performance & chip architecture in AI benchmarking. #MLPerf #NvidiaB300 #GPUcluster
🔗 aidailypost.com/news/nvidia-...
Step functions over trend lines: MLPerf® Endpoints shows only verified operating points.
No interpolation. No paper performance.
Results you can actually trust. https://bit.ly/3Pjx34u
#MLPerf
What's new in MLPerf Inference v6.0? Watch the press briefing for a walkthrough of five new benchmarks, standout results, and what it all means for the future of AI inference. ▶️
🔗 https://youtu.be/3FdkYZZlhDI
#MLPerf #MLCommons #AI #inference
MLPerf Inference v6.0 is here - our most significant benchmark update ever.
5 new & updated benchmarks. 24 submitting organizations. Industry-first tests for text-to-video and speculative decoding.
Full results: https://bit.ly/48b8NIj
#MLPerf #MLCommons
MLPerf® Endpoints uses Pareto curves to show the full performance trade-off space — not just a single number. Buyers can match results to their own use case. https://bit.ly/4bVlIiD
#MLPerf
One day out. MLPerf Inference v6.0 launches tomorrow, April 1.
Why this one's different: new benchmarks that reflect where AI is actually headed - text-to-video, speculative decoding, vision-language models, and more.
Results drop at 8 AM PDT.
#MLPerf #MLCommons #AI
MLPerf Inference v6.0 drops next Wednesday.
New benchmarks for text-to-video, speculative decoding, and VLMs.
Are you ready? #MLPerf
#MLPerf Inference v6.0 adds two LLM benchmarks: GPT-OSS 120B, a new open-weight MoE model benchmark covering math, coding & science reasoning, plus a DeepSeek-R1 interactive scenario — the first #MLPerf standard for speculative decoding.
https://bit.ly/4m19oCl
GenAI inference doesn't behave like classical ML. MLPerf® Endpoints is being designed to benchmark the full complexity of production GenAI services — not just peak numbers. mlcommons.org/2026/03/mlperf-endpoints... #MLPerf #AIBenchmarking
It’s today! 🎤
David Kanter is on stage at #GTC2026 in just a few hours — MLPerf Endpoints, the API-centric way to benchmark any Gen AI system.
📅 12–12:40 PM · San Jose Convention Center
🔗 https://bit.ly/4l5p8Uh
#MLPerf #MLCommons
Tomorrow at #GTC2026 — David Kanter on MLPerf Endpoints.
✅ Any API, any system
✅ Standardized Pareto curves
✅ Rolling submissions
✅ Transparent & reproducible
📅 March 19 · 12–12:40 PM · San Jose
🔗 https://bit.ly/4l5p8Uh
#MLPerf #MLCommons
🎉 MLPerf Mobile is now on the iOS App Store!
Run industry-standard ML benchmarks right from your iPhone.
See how your device performs — download it now 📲
https://apple.co/4bvbfdI
#MLPerf #AI #MachineLearning
Enterprise buyers, infra providers, model developers — all need AI benchmarks they can trust.
MLPerf Endpoints: standardized Pareto curves, rolling submissions, transparent results.
David Kanter at #GTC2026 · Thursday · 12–12:40 PM · San Jose
🔗 https://bit.ly/4l5p8Uh
#MLPerf #MLCommons
#GTC2026 is live! 🎉
Join us Thursday when David Kanter presents MLPerf Endpoints — API-centric benchmarking built for the Gen AI era.
📅 March 19 · 12–12:40 PM · San Jose
🔗 www.nvidia.com/gtc/session-catalog/sess...
#MLPerf #MLCommons #NVIDIA
How do you benchmark an AI system you can’t look inside?
MLPerf Endpoints: any system, any cloud, any model — one methodology.
David Kanter at #GTC2026 · March 19 · 12–12:40 PM · San Jose
🔗 www.nvidia.com/gtc/session-catalog/sess...
#MLPerf #MLCommons
🎤 David Kanter is speaking at #GTC2026!
"If It Has an API, We Can Measure It: MLPerf Enters the Gen AI Era"
📅 March 19 · 12–12:40 PM · San Jose Convention Center
🔗 https://bit.ly/4l5p8Uh
#MLPerf #MLCommons #GenAI
Results day is coming.
MLPerf Inference v6.0 drops April 1 — cross-platform AI inference data spanning datacenter, edge & more. Follow so you don't miss it.
#MLPerf #AIInference
Just saw NVIDIA’s NVFP4 recipe slash training time and costs on Blackwell Ultra GPUs—MLPerf scores are soaring and Llama 3.1 cranks out faster than ever. Want the nitty‑gritty on how GPU acceleration is reshaping LLM training? Dive in! #NVFP4 #MLPerf #Llama3_1
🔗 aidailypost.com/news/nvidias...
1/4 🧵
First Qwen model in MLPerf.
40M products daily.
Real production data from Shopify's e-commerce infrastructure.
Submit by Feb 13, 2026 👇
#MLPerf #Shopify #VLM #MLCommons
🚀 NEW: MLPerf Inference v6.0 debuts Qwen3-VL + Shopify Product Catalog benchmark
40M products daily. Real production data. First Qwen model in MLPerf.
Submit by Feb 13, 2026 →
https://bit.ly/4k9F5YS
#MLPerf #VLM #Shopify #MLCommons
MLPerf Mobile app v5.0.4 is here!
#MLPerf Mobile release now supports Samsung Exynos 2600 and Qualcomm's newest Snapdragon lineup, from flagship 8 Elite Gen 5 to mid-range 6 Gen 4. Meaning more comprehensive, apples-to-apples #AIperformance data across devices.
play.google.com/store/apps/d...
📰 AMD Umumkan Hasil MLPerf 5.1 Training Pertama untuk GPU Instinct MI350 Series
👉 Baca artikel lengkap di sini: ahmandonk.com/2025/11/19/amd-instinct-...
#ai-training #amd #gpu-computing #hardware #instinct-mi350 #mlperf #rocm
Wiwynn Achieves Record-Breaking MLPerf® Training Results with Llama 2 70B at YTL Malaysia #Malaysia #Johor #Wiwynn #MLPerf #YTL_AI_Cloud
Just saw NVIDIA’s Blackwell crush every MLPerf Training v5.1 benchmark using FP4 precision – even outpacing FP16 on Llama 3.1’s 405‑billion‑parameter model. The future of GPU AI is here. Dive in for the full breakdown! #NVIDIABlackwell #MLPerf #FP4
🔗 aidailypost.com/news/nvidia-...
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
📰 NVIDIA Dominasi MLPerf Training v5.1, Menang di Semua Benchmark
👉 Baca artikel lengkap di sini: ahmandonk.com/2025/11/13/nvidia-menang...
#ai #training #blackwell #gpu #llama #mlperf #nvidia
New Results! MLPerf Training v5.1
MLPerf Training v5.1 results are live!
Record participation: 20 organizations submitted 65 unique systems featuring 12 different accelerators. Multi-node submissions increased 86% over last year, showing the industry's focus on scale.
Results: mlcommons.org/2025/11/trai...
#MLPerf
1/3
