Inference X 🎃 by Home AgentX NEW Overview Dashboard ubenchX About Star 1,882 中文 Inference Performance Profit Estimator per GW Profit Estimator Accuracy Evals Submissions Inference Performance Profit Estimator per GW Profit Estimator Accuracy Evals Submissions Revenue & Profit Estimator (Beta) Benchmark Config Model Kimi K3 2.8T Target P90 Interactivity (tok/s/user) Cache Hit Rates Theroticial Roofline Pricing Config Token Price Moonshot list price TCO Basis External Internal Compare history Chip Config Select Chip Config
Announcing llm-d 1.0: Open distributed inference for agents on Google Cloud TPUs and GPUs