RepoAlerts

Tufalabs/tufazip

App

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change yesterday.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A deterministic decoder for a compressed artifact of the enwik9 Wikipedia text corpus, run on GPUs with an online Transformer model initialized from an offline prior. It reconstructs the 1 GB file losslessly and supports resumable checkpoints. Requires two NVIDIA B200 GPUs and…

Who it's for

Researchers and compression enthusiasts working on lossless text compression benchmarks with GPU hardware

How to use it

Install

uv sync --frozen --python 3.12.3

From its README. Check it there before running it.

Ready-made installers, when the project publishes them, are on its latest release.

Downloads (if any)

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up Tufalabs/tufazip in my project. Follow its README: https://github.com/Tufalabs/tufazip. Explain each step and check it is safe before running anything.

Star curve

851From 2 to 851 stars between 17 Oct 2026 and 22 Nov 2026.

On the radar

20 Nov 2026: #2321 Nov 2026: #10
Best place #10, on 21 Nov 2026. In the top 100 on 2 of the last 36 days.

Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.

Records

  • Best place on RepoAlerts: #10, on 21 Nov 2026
  • In the top 10 for 1 day, on 21 Nov 2026
  • In the top 100 for 2 days since 20 Nov 2026

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![Tufalabs/tufazip on RepoAlerts](https://repoalerts.com/badge/Tufalabs/tufazip.svg)](https://repoalerts.com/repo/Tufalabs/tufazip?ref=badge)
Share on X

  • haohervchb/Turing-unlock

    Research repository documenting a volatile, pre-OS tensor-compute unlock for an ASUS RTX 2080 Ti (TU102). It publishes EFI loader source, host-side tests, CUDA benchmarks and measured results showing

    ResourceModels & inferenceC · 151 stars · 32 days old

  • dangxingyu/megakernel-zoo

    Collection of LLM decoding engines, each a single persistent GPU kernel built for one specific checkpoint and GPU, written by a coding agent. Includes an OpenAI-compatible server (mkserve), an evaluat

    ResourceModels & inferenceCuda · 39 stars · +39 this week · 6 days old

  • ozguradmin/ahenk-turkish-tts

    Open Turkish text-to-speech suite: Ahenk, a VoxCPM2 LoRA for GPU with Turkish or English instructions, questions, six emotions and laughter; Ahenk Cep, an 8.6M CPU model; trnorm, a dependency-free Tur

    Models & inferencePython · 109 stars · +1 this week · 37 days old

  • raphlinus/nibnib

    An experimental image format that compresses images to 4 bits per pixel and decodes two RGB 565 pixels per input byte through a 256-entry palette of deltas. Includes a Rust encoder that uses Floyd-Ste

    LibraryRust · 171 stars · +1 this week · 24 days old · HN 188 pts

  • dkaraush/tinyasr

    Rust library for running small Zipformer2 speech recognition models on device, with streaming and full-recording decoding, punctuation, word timestamps and built-in voice activity detection. Supports

    LibraryModels & inferenceRust · 63 stars · +60 this week · 13 days old

  • KohakuBlueleaf/KohakUnlock

    Research repository on unlocking tensor-compute throughput on NVIDIA GPUs via firmware-level changes. It documents a Linux initramfs port for one TU102 card and reproduction notes for Ampere, with C s

    ResourceDev infrastructureC · 413 stars · +9 this week · 29 days old