Seismograph

What’s gaining stars on GitHub right now

Dreamer-Toby/STEPQuant

Language modelsPython#large-language-models#llm#post-training-quantization#quantization
Open on GitHub
More actions
My radar Open on Seismograph

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

About the project

A post-training quantization method for Delta-rule recurrent states: it allocates bits per state unit based on error lifetime and impact on the output. It reduces inference memory for LLMs with quantized states.

Useful for
  • Calibrate a state quantization plan for Qwen and serve it via SGLang
  • Evaluate long-generation task accuracy with 4- and 6-bit states versus FP32
  • Compare memory usage of state quantization against INT8 and INT6

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

0.3 Steady Magnitude out of 10 — how fast interest is growing, not a quality score.

Star growth looks organic. Data as of October 3, 2026, 01:56 UTC.

The star-growth assessment does not verify whether the project is safe to run.

Stars per day

01530September 27, 2026October 3, 2026

Bars show daily stars; the line is a moving average of the available history. Short histories do not yet establish a reliable usual pace. Red marks spike days.

Why it’s trending

  • The repository is 4 days old and already has 54 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
  • Top new repositories this week: #198.

Explore related projects

  1. Niko1221/Strata

    A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.

    Same category: Language models
  2. StayLameBro/backburner

    A llama.cpp fork that plugs an iPhone into a Mac over USB-C and splits the work: the Mac runs layers 1-40, the iPhone runs 41-64 on its GPU, speeding up prefill and allowing context up to 196k-229k tokens. Aimed at…

    Same category: Language models
  3. Kutuyyy/Leaked-System-Prompt-AI

    A repository that collects and documents system prompts, instructions, and tool definitions of major AI models and agent platforms (OpenAI, Anthropic, Google, Cursor, Devin, etc.) for studying their behavior.

    Same category: Language models

Three GitHub discoveries every day

What they do, why they are gaining interest, and what to check before using them.

Get discoveries in TelegramRead Daily Radar
Share on X Telegram

Numbers

Total stars
54
Today
0 · ≈ 1 by evening
Forks
0
Issues and pull requests
0
Watchers
0
Language
Python
Created
September 29, 2026
Last push
October 1, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in
README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

Seismograph: 0.3 
[![Seismograph](https://gitnova.dev/badge/Dreamer-Toby/STEPQuant.svg?lang=en)](https://gitnova.dev/en/r/Dreamer-Toby/STEPQuant)