Anthropic：Claude 自主完成 AMD GPU 适配，3 天移植近 100% 内核
Anthropic 让 Claude 自己把 Claude 跑上 AMD GPU，3 天搞定，以前要几十个工程师干几个月。内核移植这种底层活 AI 也能干了，做基础设施和芯片生态的人应该看看这条。
Anthropic 在 Road Show 视频中披露：今年首次接入 AMD GPU 时，团队让名为 Mythos 的智能体尝试适配，仅用 3 天就让 Claude 跑上 AMD 硬件，期间几乎没有人工干预。Claude 移植或编写了近 100% 的内核代码。对比以往，接入一个新芯片平台通常需要数十名工程师投入数月的移植工作。
这说明 Claude 已经能承担底层系统级编程任务——GPU 内核移植涉及 CUDA/ROCm 等底层代码改写，过去是高人力成本的手工活。Anthropic 将其视为智能体在基础设施工程中的实际落地案例，而非仅限于应用层编码。
对行业而言，芯片适配周期从“数月+数十人”压缩到“3 天+智能体”，可能改变硬件厂商与 AI 实验室的合作门槛。AMD 等英伟达之外的芯片供应商若能借智能体快速完成生态适配，开发者切换硬件平台的成本将显著降低。
From the Anthropic Road Show video: 'This has also made us really good at bringing up new chips. As an example, this year, we started working with AMD GPUs for the first time. In the past, bringing on a new chip platform took dozens of engineers months of work. This time we had Mythos try it out. It got Claude running on AMD in just 3 days with basically no human intervention. Claude ported or wrote almost 100% of the kernels.'
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude, Anthropic, AMD, 智能体.
Source attribution: curated from Andrew Curran (@AndrewCurran_). Cross-source corroboration: 11 independent sources have covered this development (including theverge, kimmonismus, 宝玉), confirming industry-wide signal strength.
