# nanovlm

Published articles for nanovlm.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Efficient MultiModal Data Pipeline

DevFeed: [Efficient MultiModal Data Pipeline](<https://devfeed.tech/articles/efficient-multimodal-data-pipeline-7355.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/mmdp>)

Author: Aritra Roy Gosthipaty; Luis; Andres Marafioti; Sergio Paniego; Pedro Cuenca

Published: 2025-07-08T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [multimodal](<https://devfeed.tech/topics/multimodal.md>), [data](<https://devfeed.tech/topics/data.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Mathematics](<https://devfeed.tech/topics/mathematics.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [batching](<https://devfeed.tech/tags/batching.md>), [community](<https://devfeed.tech/tags/community.md>), [data](<https://devfeed.tech/tags/data.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nanovlm](<https://devfeed.tech/tags/nanovlm.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [research](<https://devfeed.tech/tags/research.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

This article explains how to build an efficient multimodal data pipeline for nanoVLM training. It examines waste caused by idle GPUs and excessive padding, then introduces progressively improved data preparation and batching strategies, including a knapsack-based approach to fit more useful data into each batch.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## KV Cache from scratch in nanoVLM

DevFeed: [KV Cache from scratch in nanoVLM](<https://devfeed.tech/articles/kv-cache-from-scratch-in-nanovlm-7304.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/kv-cache>)

Author: Aritra Roy Gosthipaty; Kashif Rasul; Luis; Andres Marafioti; Pedro Cuenca

Published: 2025-06-04T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Caching](<https://devfeed.tech/topics/caching.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>)

Tags: [cache](<https://devfeed.tech/tags/cache.md>), [generate](<https://devfeed.tech/tags/generate.md>), [inference](<https://devfeed.tech/tags/inference.md>), [nanovlm](<https://devfeed.tech/tags/nanovlm.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [transformers](<https://devfeed.tech/tags/transformers.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

The article explains how KV Caching was implemented from scratch in the nanoVLM repository using pure PyTorch, reporting a 38% generation speedup. It describes the sequential nature of autoregressive language-model generation, the repeated computation in transformer self-attention, and how caching previously computed key and value tensors reduces this redundancy.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## nanoVLM: The simplest repository to train your VLM in pure PyTorch

DevFeed: [nanoVLM: The simplest repository to train your VLM in pure PyTorch](<https://devfeed.tech/articles/nanovlm-the-simplest-repository-to-train-your-vlm-in-pure-pytorch-7363.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/nanovlm>)

Author: Aritra Roy Gosthipaty; Luis; Andres Marafioti; Sergio Paniego; merve; Pedro Cuenca; Vaibhav Srivastav

Published: 2025-05-21T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [llama](<https://devfeed.tech/topics/llama.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [community](<https://devfeed.tech/tags/community.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llm](<https://devfeed.tech/tags/llm.md>), [nanovlm](<https://devfeed.tech/tags/nanovlm.md>), [object-detection](<https://devfeed.tech/tags/object-detection.md>), [open](<https://devfeed.tech/tags/open.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [research](<https://devfeed.tech/tags/research.md>), [train](<https://devfeed.tech/tags/train.md>), [training](<https://devfeed.tech/tags/training.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

nanoVLM is a minimal, readable pure-PyTorch toolkit for building and training vision-language models. It processes images and text to generate text, focuses on visual question answering, and is designed to help beginners explore VLMs through a compact codebase and guided training workflow.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.