面壁智能 OpenBMB 宣布 MiniCPM-OCR 1.0 已原生支持 vLLM 和 SGLang,代码已合并、可直接部署,将模型接入两个主流 LLM 推理框架。作者称这带来更简单的集成和更灵活的部署,OCR 能力保持不变。
🚀 MiniCPM-OCR 1.0 now has native support for vLLM and SGLang!
Already merged and ready to deploy, bringing MiniCPM-OCR into two widely used LLM inference frameworks.
⚡ Easier integration. More flexible deployment. Same powerful OCR capabilities.
Built to fit right into your stack. 🔥
在 X 查看被引用的帖子Your OCR says it’s done—but did it get everything right? 🤔 In high-stakes workflows, even a small error can be costly.
🚀 Meet the MiniCPM-OCR suite: an open-source solution to parse fast and guard the results.
Two new models:
🔹 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. Compact, accurate, and fast.
🔹 MiniCPM-OCR Jev — A 2B decision model that helps assess parsing accuracy, with performance approaching that of Qwen3.5-397B-A17B on JevOCRBench.⚡ What’s new?
Small model, SOTA results: MiniCPM-OCR 1.0 scores 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2.A sharp goalkeeper 🛡️: MiniCPM-OCR Jev is model-agnostic, checking text, formulas, and tables from different OCR parsers. It achieves 93.6 on JevOCRBench, outperforming JEV-35B-A3B (90.1) and approaching Qwen3.5-397B-A17B (93.8).
Up to 128 pages per minute 🤯: With DSpark, MiniCPM-OCR runs at 1.49× the speed of PaddleOCR-VL-1.6 and 3.62× that of MinerU2.5 Pro. The SDK’s concurrency optimizations further boost throughput to as much as 128 pages per minute.
Deploy where you work: Day-0 support for Arm, Houmo AI, Intel, and NVIDIA, plus 10 more chip vendors through FlagOS.
Ready for your stack: vLLM, SGLang, llama.cpp, and Ollama, with quantized models, fine-tuning support, and Agent Skills.
🔗 GitHub: github.com/OpenBMB/MiniCPM-OCR
🤗 Hugging Face:
MiniCPM-OCR 1.0:huggingface.co/openbmb/MiniCP…
MiniCPM-OCR Jev:huggingface.co/openbmb/MiniCP…
👉 Try the Demo:platform.modelbest.ai/console…
Use the API:platform.modelbest.ai/console…
来源:OpenBMB · x.com