Prashanth Lande·Oct 29Serving an OCR Model in Production with vLLM: What It Does and What I LearnedI served an open-source OCR model with vLLM, benchmarked it on one GPU, and watched it in production. Here’s what each step taught me.
Prashanth Lande·Oct 16From Fear to Confidence: What Using AI Every Day Taught Me as an EngineerThe fear everyone is talking about
Prashanth Lande·Oct 8Why 80% Accuracy Can Mean 0% Found: Accuracy, Precision, Recall and F1 ExplainedAfter training a model, you get a few numbers back: accuracy, precision, recall and F1. It is tempting to look at one of them and move on…A response icon2A response icon2
Prashanth Lande·Oct 2Beyond OCR: How Docling Let Me Upgrade to a Vision-Language Model Without Rewriting My PipelineChoosing a document parser for its output format, not just its OCR accuracy, turned out to be the best decision I made for my pipeline…