AMD 攜手 Hugging Face：推出 optimum-amd 實現 AMD GPU 的大語言模型即開即用加速
Original: AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU
Hugging Face's official blog announced a deep partnership with chip giant AMD, launching `optimum-amd`, an open-source library optimized…
Hugging Face 宣布與 AMD 深度合作，推出 optimum-amd 套件，旨在簡化 AMD GPU（如 Instinct 與 Radeon 系列）上的模型部署與加速。該套件整合了 AMD ROCm 軟體平台，開發者只需修改幾行程式碼，即可在 AMD 硬體上無縫運行並加速主流的大語言模型（LLM）。此舉打破了過去 NVIDIA CUDA 在 AI 訓練與推理上的壟斷，為企業與開發者提供更具性價比的硬體選擇。
Hugging Face's official blog announced a deep partnership with chip giant AMD, launching `optimum-amd`, an open-source library optimized specifically for AMD hardware. This collaboration aims to address the AI developer community's heavy dependence on NVIDIA's CUDA ecosystem, injecting more diverse and competitive hardware options into the market.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.