NVIDIA Cites SemiAnalysis AgentX: Rubin NVL72 Shows 30x Better Throughput
nvidia · x · 2026-08-29
NVIDIA highlighted SemiAnalysis's AgentX 1.0, the first open-source, multi-turn agentic coding inference benchmark with 1M context length. Tests indicate that Vera Rubin NVL72 achieves up to 30x better throughput per megawatt compared to GB300 NVL72 on this workload. AgentX replaces fixed sequence length metrics with realistic scenarios featuring long context, high prefill reuse, sub-agent bursts, and KV cache offloading. The $3M dataset is now open source.
More from Infra
- Google expands Android Earthquake Alerts from 98 to nearly 200 countries after 1B+ alerts — sundarpichai · 2026-10-16
- Microsoft's Magnetar zkVM proves programs 10-39x faster using only standard hash functions — Microsoft Research · 2026-10-16
- Moving 1PB back on-premises costs a fortune as AI training drives cloud repatriation — DavidLinthicum · 2026-10-15
- FP8 + DSpark stack delivers ~2x speedup for Nemotron 3.5 Super VL on H100s — vllm_project · 2026-10-15
- Nemotron 3.5 Super VL hits ~630 tokens/s at 100k-token prompts, fastest 20+ score model measured — ArtificialAnlys · 2026-10-15
- vLLM Ships Day-0 Support for Nemotron 3.5 Super VL with NVFP4 on a Single GB200 — vllm_project · 2026-10-15