使用 ONNX Runtime 加速超過 130,000 個 Hugging Face 模型
Original: Accelerating over 130,000 Hugging Face models with ONNX Runtime
Hugging Face officially announced a deep collaboration with Microsoft to integrate ONNX Runtime (ORT) into the Hugging Face ecosystem. This…
Hugging Face 宣布與微軟 ONNX Runtime 深度整合，Hub 上超過 13 萬個模型現在能輕鬆轉換並加速。開發者只需透過 Hugging Face Optimum 庫，即可在 CPU 和 GPU 上實現顯著的推理延遲降低與吞吐量提升。此舉大幅降低了開源模型在生產環境中的部署門檻與硬體成本。
Hugging Face officially announced a deep collaboration with Microsoft to integrate ONNX Runtime (ORT) into the Hugging Face ecosystem. This partnership enables more than 130,000 pre-trained models on the Hugging Face Hub to directly leverage ONNX Runtime for inference acceleration, covering multiple modalities including natural language processing (NLP), computer vision (CV), and speech.
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 →Related
Summaries are AI-generated; the original article is authoritative.