InferenceX
InferenceX, launched in October 2025 under the name InferenceMAX, is an open-source benchmark that continuously measures large language model inference performance across AI accelerators and serving software.
AI Hardware
Explore AI Hardware through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: AI Benchmarks
Articles that also belong to these categories. Counts cover all of AI Hardware.
All articles (355)AI Infrastructure (98)AI Companies (85)NVIDIA (61)Robotics (44)Chinese AI (37)Data Centers (36)AI Inference (30)Google (24)AI Tools & Products (18)AI Policy & Regulation (17)Machine Learning (17)Artificial Intelligence (10)Computer Science (10)Meta AI (10)Open Source AI (9)Autonomous Vehicles (7)Deep Learning (6)Developer Tools (5)Embodied AI (5)Humanoid Robots (5)Microsoft (5)Computer Vision (4)Large Language Models (4)Robotics Companies (4)AI Benchmarks (3)AI Models (3)Algorithms (3)Neural Networks (3)OpenAI (3)People (3)Training & Optimization (3)AI History (2)AI for Science (2)Edge computing (2)Google DeepMind (2)Healthcare AI (2)Multimodal AI (2)Reinforcement Learning (2)AI Energy (1)AI Ethics (1)Enterprise AI (1)Finance AI (1)Generative AI (1)Image Generation (1)MLOps (1)Mathematics (1)Physical AI (1)Robot Hardware (1)Small Language Models (1)Transformer Models (1)Video Generation (1)
Showing 1-3 of 3 articles
MLPerf
MLPerf is the AI industry's standard suite of benchmarks for measuring how fast machine learning systems train and run models, developed and maintained by MLCommons
Tokens per second
Tokens per second (TPS) is a key performance metric for measuring the speed of large language model (LLM) inference. It quantifies how many tokens a model can generate or process in one second.