Featured Articles
New MLPerf Inference v4.1 Benchmark Results Highlight Rapid Hardware and Software Innovations in Generative AI Systems
New mixture of experts benchmark tracks emerging architectures for AI models
Mixtral 8x7B: a new MLPerf Inference benchmark for mixture of experts
MLPerf task force shares insights on the design of its mixture of experts large language model benchmark
SDXL: An MLPerf Inference benchmark for text-to-image generation
MLPerf task force shares insights on the design of its text-to-image benchmark
Announcing the results of the inaugural AlgoPerf: Training Algorithms benchmark competition
Non-diagonal preconditioning has dethroned Nesterov Adam, and our self-tuning track has crowned a new state-of-the-art for completely hyperparameter-free training algorithms
MLCommons AI Safety Working Group’s Rapid Progress to a v1.0 Release
Building a comprehensive approach to measuring the safety of LLMs and beyond
New MLPerf Training Benchmark Results Highlight Hardware and Software Innovations in AI Systems
Two new benchmarks added – highlighting language model fine-tuning and classification for graph data
Blog
-
Mixtral 8x7B: a new MLPerf Inference benchmark for mixture of experts
MLPerf task force shares insights on the design of its mixture of experts large language model benchmark
-
SDXL: An MLPerf Inference benchmark for text-to-image generation
MLPerf task force shares insights on the design of its text-to-image benchmark
-
Comprehensive Open Federated Ecosystem (COFE) Presented at ISBI 2024
MLCommons Medical working group demonstrates COFE at ISBI
News
-
New MLPerf Inference v4.1 Benchmark Results Highlight Rapid Hardware and Software Innovations in Generative AI Systems
New mixture of experts benchmark tracks emerging architectures for AI models
-
Announcing the results of the inaugural AlgoPerf: Training Algorithms benchmark competition
Non-diagonal preconditioning has dethroned Nesterov Adam, and our self-tuning track has crowned a new state-of-the-art for completely hyperparameter-free training algorithms
-
MLCommons AI Safety Working Group’s Rapid Progress to a v1.0 Release
Building a comprehensive approach to measuring the safety of LLMs and beyond