OpenAI Jalapeño Outperforms Nvidia Rubin with Massive Software Gains in 5 Days
teortaxesTex · x · 2026-08-26
Analysis by SemiAnalysis reveals OpenAI's custom Jalapeño chip surpasses Nvidia's Vera Rubin in throughput and performance-per-watt, even without Prefill/Decode disaggregation or speculative decoding used by Rubin. This suggests a more balanced design less reliant on P/D disagg. Additionally, the 5-day gap between performance curves highlights OpenAI's rapid software iteration speed.
More from Infra
- engy.ai processes 50B+ tokens in a day as open-model inference demand surges — const_reborn · 2026-10-16
- New inference engine 'e' hits 10,500 tok/s on a single DGX Station — brandon_galang · 2026-10-16
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16