MiniCPM-OCR 原生支持 vLLM 与 SGLang
🚀 MiniCPM-OCR 🤝 vLLM & SGLang
面壁智能宣布 MiniCPM-OCR 已原生支持 vLLM 和 SGLang 两个开源推理框架,方便开发者将其集成到现有工作流中。
查看原帖你的 OCR 说它完成了——但它真的全都识别对了吗?🤔 在高风险工作流中,哪怕一个小错误也可能代价高昂。 🚀 认识一下 MiniCPM-OCR 套件:一个开源解决方案,既能快速解析,又能守护结果。 两个新模型: 🔹 MiniCPM-OCR 1.0 — 在 1B 规模下实现 SOTA 级 OCR 性能与速度。紧凑、准确、快速。 🔹 MiniCPM-OCR Jev — 一个 2B 决策模型,帮助评估解析准确率,在 JevOCRBench 上的表现接近 Qwen3.5-397B-A17B。 ⚡ 有哪些新亮点? 小模型,SOTA 结果:MiniCPM-OCR 1.0 在 Real5-OmniDocBench 上得分 93.68,在 OCRBench v2 上得分 54.7。 一位敏锐的守门员 🛡️:MiniCPM-OCR Jev 与模型无关,可检查来自不同 OCR 解析器的文本、公式和表格。它在 JevOCRBench 上达到 93.6,优于 JEV-35B-A3B(90.1),并接近 Qwen3.5-397B-A17B(93.8)。 每分钟最多 128 页 🤯:借助 DSpark,MiniCPM-OCR 的运行速度是 PaddleOCR-VL-1.6 的 1.49 倍,是 MinerU2.5 Pro 的 3.62 倍。SDK 的并发优化进一步将吞吐量提升至每分钟最多 128 页。 在你工作的地方部署:首日即支持 Arm、后摩智能、Intel 和 NVIDIA,并通过 FlagOS 支持另外 10 多家芯片厂商。 适配你的技术栈:vLLM、SGLang、llama.cpp 和 Ollama,并提供量化模型、微调支持和 Agent Skills。 🔗 GitHub:https://t.co/2SlATAJk08 🤗 Hugging Face: MiniCPM-OCR 1.0:https://t.co/i347di4Fju MiniCPM-OCR Jev:https://t.co/ayVzhCJenh 👉 试用 Demo:https://t.co/QsFAJT3AFy 使用 API:https://t.co/dP01jBS2j2
查看原文
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: https://t.co/2SlATAJk08 🤗 Hugging Face: MiniCPM-OCR 1.0:https://t.co/i347di4Fju MiniCPM-OCR Jev:https://t.co/ayVzhCJenh 👉 Try the Demo:https://t.co/QsFAJT3AFy Use the API:https://t.co/dP01jBS2j2
正文
🚀 MiniCPM-OCR 🤝 vLLM & SGLang
Native support for two leading open-source inference frameworks — @vllm_project and @sgl_project — making it easier for developers to integrate MiniCPM-OCR into their existing workflows.
⚡ Powerful OCR, flexible deployment, and a growing open-source ecosystem.