# LlamaIndex speeds up OCRia-1 nearly 10x on a single B200 GPU

> Original title: We got OCRia-1 generating tokens nearly 10× faster on a single B200.

- Source: LlamaIndex
- Published: 2026-11-03T16:49:05.000Z
- Bad Influence: https://badinfluence.news/items/u8m3ig4pyayybmkgw8wq7dlwx
- Original: https://x.com/llama_index/status/2117660347087626402

## Summary

LlamaIndex says it made OCRia-1 generate tokens nearly 10 times faster on a single B200 GPU through 17 inference optimizations, each tested for both speed and accuracy. Some individual changes improved speed by only 2–5%, which the company says added up. LlamaIndex plans to contribute some of these optimizations back to the open-source vLLM project.

## Post

We got OCRia-1 generating tokens nearly 10× faster on a single B200.

Getting there meant making much better use of the same GPU. We tuned how OCRia-1 runs for the demands of document parsing, testing every change for both speed and accuracy.

Some improvements were only 2–5%. Seventeen smaller optimizations later, “just a few percent” starts adding up.

Our infrastructure team wrote up what worked, how they tested the changes, and what they learned about making document models run faster.

We also plan to contribute some of these optimizations back to the open-source vLLM project. Read the full breakdown →
https://www.llamaindex.ai/blog/the-inference-stack-behind-ocria

Watch the video below to see OCRia-1’s token generation before and after the optimizations.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fext_tw_video_thumb%2F2117660335075155968%2Fpu%2Fimg%2F-oKtgQPkX1lVZBla.jpg&mode=thumb&exp=1793923200&sig=d4bacf597cc10dc2)