NeuroFlow 55.8x video inference speedup for Vision Transformers PyTorch

What it does

TL;DR: Vision Transformers waste 90% of their compute recalculating stationary asphalt. NeuroFlow tracks semantic surprise in embedding space, physically eliminating background tokens before the encoder. Left: Standard SigLIP FP16 processing 100% of tokens (~722ms) @1792p. Right: NeuroFlow Architecture B eliminating 98% of stationary tokens before the encoder (~15ms) @1792p. This repository contains the official PyTorch implementation, verification scripts, and pre-print paper for NeuroFlow . NeuroFlow is a dynamic routing framework for Vision Transformer video inference. It exploits temporal redundancy by tracking per-patch embedding-distance threshold via an Exponential Moving Average…from github.com

• 
  DeepDream for Video with Temporal ConsistencyJan 2026 · github.com · ▲72

  I forked a PyTorch DeepDream implementation and added video support with temporal consistency. It produces smooth DeepDream videos with minimal flickering, and is highly flexible including many parameters and supports multiple pretrained image classifiers including GoogLeNet. Check out the repo for sample videos! Features: - Optical flow warps previous hallucinations into the current frame - Occlusion masking prevents ghosting and hallucination transfer when objects move - Advanced parameters (layers, octaves, iterations) still work - Works on GPU, CPU, and Apple Silicon

• 
  Fast Style Transfer in TensorFlow2016 · github.com · ▲184

  TensorFlow CNN for fast style transfer ⚡🖥🎨🖼. Contribute to lengstrom/fast-style-transfer development by creating an account on GitHub.

• 
  Neuropod – Uber ATG's open source deep learning inference engine2020 · github.com · ▲80

  A uniform interface to run deep learning models from multiple frameworks - uber/neuropod

• 
  TensorFire2017 · tenso.rs · ▲99

  Blazing-fast in-browser neural networks

• 
  Faster R-CNN object detector implemented in PyTorch and TensorFlow 22022 · github.com · ▲15

  Fresh and (I think) clean implementations of Faster R-CNN in PyTorch and TensorFlow 2/Keras. I wanted to learn about object detectors and decided to understand and implement a foundational model in the field, Faster R-CNN (elements of which are still used in modern models to this day), using the paper alone. That proved to be more difficult than expected and I had to relent and take a peak at existing implementations to fill in some important gaps. I've documented my struggles and learnings in the README for others to benefit from. I also wanted to solidify my understanding of…

• AT
  A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)Aug 2026 · mikeayles.com · ▲79

  A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.

• 
  SimCity, but with Permits▲930

  A free city-building game in your browser. You are the mayor. You know what the city needs. Now get it past the zoning board, the neighbors, the appeals court and the next election.

  Life & fun · 2d ago · permit.petercai.com

• IV
  I've been paying for a rural Tanzanian's education for 10 years▲778

  Life & fun · 15d ago · tanzaniaeducationproject.org

• 
  Bigwords.page – Turn any screen into a sign. The URL is the app▲728

  Turn a phone, tablet or TV into a sign. Type a message and it fills the screen: welcome signs, timers, Wi-Fi passwords and more. No app, no account, free.

  Life & fun · 15d ago · bigwords.page

• 
  Guitoro, a virtual guitar you strum with your keyboard▲573

  Play a free virtual guitar online with your keyboard or by touch. Slow songs down and see every chord, string and strum. Acoustic, classic, electric and bass.

  Life & fun · 9d ago · guitoro.com

• 
  See *almost* any carriers phone settings▲432

  Carrier settings from iPhone, Pixel and Galaxy firmware, decoded and compared: APNs, VoLTE, 5G and Wi-Fi Calling per carrier, and what each build changed.

  Life & fun · 13d ago · carrierexplode.com

• 
  The whole Solar System and every tracked satellite, live in the browser▲407

  Life & fun · 23d ago · space.bl2.net

• 
  Brew ▲900

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲896

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲806

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲795

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• 
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• 
  Files.md – Open-source alternative to Obsidian▲730

  🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

  Dev tools · May 2026 · github.com