AI 精选动态
智能评分 65
Tensordyne 发布 Napier 推理芯片
AI 推荐理由
披露了通过硬件对数运算提升能效的具体技术路径，并提供了针对 DeepSeek-R1 的量化对比数据。核心解读
Tensordyne 发布 Napier 推理芯片，采用 TSMC 3nm 工艺。该芯片通过硬件实现对数数学运算将乘法转换为加法，声称其每瓦 token 数和吞吐量分别是 NVIDIA Blackwell 的 17 倍和 13 倍。在 DeepSeek-R1 测试中，单机架吞吐量为 363K tokens/sec，而 NVIDIA 对比系统为 27.4K tokens/sec。
全文
Tensordyne just announced a breakthrough Inference system.
Logarithmic AI compute chips which is 17x more tokens per watt and 13x higher throughput than NVIDIA Blackwell.
The main math advance they say they unlocked is efficient logarithmic math directly in hardware. In log space, multiplication turns into addition, which is much easier to build than multiplier circuits
That allows smaller compute circuits on the chip than today’s FP8 and INT8 GPUs.With fewer transistors, the chips stay cooler and use less energy, while the extra die space can hold more tensor engines, additional high-bandwidth SRAM and HBM3e memory, plus a fast interconnect fabric.
For DeepSeek-R1, Tensordyne claims 363K tokens/sec per rack versus 27.4K for Nvidia’s comparison system
They have successfully completed tape-out of the Napier processor, which is now in production at TSMC on its 3nm process node.
> **引用原帖 Tensordyne (@TensordyneInc):**
> https://t.co/s5e3TQ6E9Z
> https://x.com/TensordyneInc/status/2066567307984531834
Rohan Paul (@rohanpaul_ai): This is their more detailed technical report.
https://t.co/tDCueNWgFt