OpenAI reveals Jalapeno chip: B200-level throughput with novel speculate-decode split
appenz · x · 2026-08-26
OpenAI showcased its Jalapeno chip at HotChips. It offers throughput comparable to a B200 but with lower power consumption and higher efficiency at high token rates. The most notable feature is the separation of Speculate and Decode into distinct phases using different models, a novel architectural approach.
Related event: OpenAI Unveils Jalapeño, Its First Custom Inference ASIC, at Hot Chips(7 posts)→
More from Infra
- NVIDIA and Sweden's Wallenberg launch Sferical One, a shared AI supercomputer — nvidia · 2026-10-16
- Next infra frontier: self-evolving systems that adapt and self-verify — _shreya_s · 2026-10-16
- Xiaomi's MiMo RL dashboard reveals $3.47M spent on just 30 training steps — bycloud · 2026-10-16
- Cerebras pushes disaggregated inference: heterogeneous prefill pools feeding wafer-scale decode — ai · 2026-10-16
- d-Matrix GA's Corsair rackscale, demos first public Attention-FFN disaggregation at 845 tok/s — ai · 2026-10-16
- Actual's inference engine hits 10k tok/s on NVIDIA DGX Station, GB300 case study — natesiggard · 2026-10-16