Robuta

Sep 24, 2025 - A New TinyML Streaming Benchmark for MLPerf Tiny v1.3

Nov 13, 2025 - MLCommons® announced new results for the MLPerf® Training v5.1 benchmark suite, highlighting the rapid evolution and increasing richness of the AI ecosystem...

Graphcore researchers and engineers explain how they achieved dramatic performance results for the popular computer vision model.

Nov 27, 2025 - Wiwynn Delivers Best MLPerf Training v5.1 Llama 2 70B LoRA Results YTL Malaysia Data Center

Sep 9, 2025 - MLCommons MLPerf Inference v5.1 Benchmarking the Next Generation of Reasoning LLMs with Long Output Sequences

Lambda's NVIDIA GB300 NVL72 cluster boosts LLM training performance by 27% in MLCommons MLPerf benchmarks v5.1, setting a new MLCommons standard for enterprise...

Jul 1, 2025 - MLCommons' latest MLPerf Inference v5.0 results show Gen AI now the center of attention for performance engineering.

Sep 17, 2025 - New data reveals advances in tiny neural network performance

Sep 2, 2025 - MLCommons Releases MLPerf Client v1.0 with Expanded Models, Prompts, and Hardware Support, Standardizing AI PC Performance.

Graphcore continues to deliver significant performance gains at MLPerf thanks to software optimisation and new flexible and efficient scale-out systems,...

我们在先进的 AI 性能行业基准测试中的结果。

Aug 15, 2025 - The MLPerf Tiny working group develops Tiny ML benchmarks to evaluate inference performance on ultra-low-power systems.

Oct 29, 2025 - MLPerf Training updates its text-to-image benchmark to Flux.1, a powerful 11.9B parameter transformer model. Learn about the new standard in generative AI...

Nov 13, 2025 - In MLPerf Training v5.1, NVIDIA swept all seven tests, delivering the fastest time to train across LLMs, image generation, recommender systems, computer vision...

Sep 2, 2025 - MLCommons has developed a new automotive benchmark for MLPerf Inference v5.0 based on established industry methods such as PointPainting, DeepLabv3+, and the...

Nov 14, 2025 - Today, MLCommons announced new results for the MLPerf Training v5.1 benchmark suite, highlighting the rapid evolution and increasing richness of the AI...

Aug 15, 2025 - Create an application that contains a set of fair and representative machine-learning benchmarks for client consumer systems.

Jun 26, 2025 - New MLCommons MLPerf Training v5.0 Benchmark Results Reflect Rapid Growth and Evolution of the Field of AI

Sep 2, 2025 - New checkpoint benchmarks provide “must-have” information for optimizing AI training

Nov 17, 2022 - How fast is your machine learning infrastructure, and how do you measure it? That's the topic of this episode with David Kanter of MLCommons.

Oct 22, 2025 - MLPerf Training Benchmark has emerged as the industry's critical standardization tool for evaluating AI infrastructure performance. Learn more.

Nov 18, 2024 - The MLPerf Storage working group defines and develops the MLPerf Storage benchmarks to characterize performance of storage systems that support machine...

Our results for the leading industry benchmark for AI performance.

Aug 15, 2025 - The MLCommons MLPerf Inference working group creates a set of fair and representative inference benchmarks. The myriad combinations of ML hardware and software...

Sep 23, 2025 - The MLPerf Training working group creates and runs benchmarks that measure the performance of training ML models on a wide variety of use cases, software, and...

Graphcore's MLPerf submissions show big performance gains on ResNet and BERT while Baidu's PaddlePaddle submission reflects the growing IPU ecosystem.

Graphcore shares outstanding performance results in first ever training submission to MLPerf, AI's most widely recognised comparative benchmarking process.

MLPerf Inference v5.1, Blackwell inference performance, B200 benchmarks, real-world AI inference, low latency inference for real-time assistants, inference...

Sep 9, 2025 - MLCommons introduces a new speech-to-text benchmark based on established industry methods such as Whisper-Large-V3 and the LibriSpeech dataset.

Nov 17, 2025 - MLPerf Client is a new benchmark developed valuate the performance of large language models (LLMs) and other AI workloads on personal computers–from laptops...

Sep 2, 2025 - MLCommons, MLPerf Storage v2.0 Addressing Backup and Recovery Speed for Training Large Language Models on Scale-Out Clusters

Sep 9, 2025 - Its GB200 NVL72 system delivered up to 30 times higher throughput on the Llama 3.1 405B workload compared to firm’s H200 NVL8, Nvidia said.

Oct 29, 2025 - MLPerf Training v5.1 introduces the Llama 3.1 8B benchmark, offering an accessible way to evaluate modern LLM pretraining on single-node systems, replacing the...

Aug 27, 2025 - The MLPerf Automotive working group defines and develops an industry standard ML benchmark suite for automotive to be used in request for information (RFIs)...

Sep 4, 2025 - MLCommons announces new RGAT benchmark to MLPerf Inference v5.0 - addresses performance tests for graph-structured data and applications.

8 月 5 日，全球权威 AI 工程联盟 MLCommons 发布了最新的 MLPerf® Storage v2.0...

Sep 9, 2025 - MLCommons Releases New MLPerf Inference v5.1 Benchmark ResultsNew results highlight AI industry’s latest technical advances

Sep 2, 2025 - AVCC® and MLCommons® announced new results for their new MLPerf® Automotive v0.5 benchmark

Sep 4, 2025 - The MLPerf Automotive benchmark suite measures the performance of computers intended for automotive, both for Advanced Driving Assistance System/Autonomous...

Sep 9, 2025 - MLCommons introduces a new small language model benchmark based on established industry methods such as Llama3.1-8B, vLLM, and the CNN-DailyMail dataset.

Sep 2, 2025 - MLCommons MLPerf Training Expands with Llama 3.1 405B

Nov 17, 2025 - MLPerf Client v1.5 introduces Windows ML support, expanded platform coverage (including iPad), and experimental power measurement, setting a new, comprehensive...