SemiAnalysis: OpenAI's Jalapeño Is a General-Purpose Inference ASIC Beating NVIDIA and AMD in Tests
zephyr_z9 · x · 2026-08-25
SemiAnalysis shares more details on OpenAI's Jalapeño chip:
- Not narrowly optimized for OpenAI models — it's a general-purpose LLM inference ASIC, designed from scratch, going from team buildout to tape-out in roughly 16 months.
- In their tested workloads it outperformed NVIDIA, AMD and Google accelerators on several inference efficiency metrics.
- Performance: DeepSeek R1 exceeded 700 tokens/sec/user at concurrency 1; Kimi K2.5 and GPT-OSS reached roughly 1,400 tokens/sec/user in selected tests.
- These results used single-token prediction, without speculative decoding or prefill/decode disaggregation.
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