PulseAugur
EN
LIVE 02:27:14

Together AI benchmarks Blackwell hardware for agent infrastructure

Together AI has released benchmarks demonstrating the performance of their inference stack on NVIDIA's Blackwell hardware, showing a 31% increase in transactions per second compared to other open-source engines. This performance boost is attributed to custom kernels optimized for Blackwell's Tensor Cores. The company's coding agents, which are used by Cursor, run on this infrastructure, and Together AI has also introduced AgentPerf, a new benchmark for evaluating AI agent performance. AI

IMPACT Demonstrates hardware optimization for AI agent infrastructure, potentially improving real-time coding agent performance.

RANK_REASON The cluster details benchmarks and performance metrics for AI inference infrastructure, which falls under research.

Read on X — Together (inference / OSS) →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Together AI benchmarks Blackwell hardware for agent infrastructure

COVERAGE [2]

  1. X — Together (inference / OSS) TIER_1 English(EN) · togethercompute ·

    Read about Cursor: https://t.co/sxFWpHMR1p https://t.co/9PgM6g2AfP

    Read about Cursor: https://t.co/sxFWpHMR1p https://t.co/9PgM6g2AfP

  2. X — Together (inference / OSS) TIER_1 English(EN) · togethercompute ·

    The case for Blackwell in production agent infrastructure just got cleaner.

    The case for Blackwell in production agent infrastructure just got cleaner. @ArtificialAnlys AgentPerf gives the hardware picture. Together's coding agent benchmarks give the inference picture: 31% more TPS than the next-fastest OSS engine on the same hardware, through custom