Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Busbar
Busbar
OfinTech Desk
OfinTech Desk
Omnigraph
Omnigraph
It's a plan
It's a plan
Bifrost
Bifrost

kindlingai/gr8

A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash

#LLM inference
Visit GitHub
Cuda
86
16
8 contributors
MIT License
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Busbar

Control what AI can do before it acts

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast kindlingai/gr8 is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Oct 10 – Nov 20, 2026

Stars +65 in 42 days

0510
8

Forks +16 in 42 days

024
4

Merged PRs 437 in 42 days

02040
36

Trendshift Trendingwhere the repository ranked each day it made the top 25

Top 25 in Cuda

2531207231819194156258657152067134118
Oct 10Oct 16Oct 22Oct 28Nov 3Nov 9Nov 15
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRsCuda
Sat, Oct 10, 2026+0+28Not trending
Sun, Oct 11, 2026+0+123Not trending
Mon, Oct 12, 2026+0+16Not trending
Tue, Oct 13, 2026+0+29#25
Wed, Oct 14, 2026+7+26#3
Thu, Oct 15, 2026+5+19#1
Fri, Oct 16, 2026+1+09#20
Sat, Oct 17, 2026+2+08#7
Sun, Oct 18, 2026+0+010#23
Mon, Oct 19, 2026+2+00#18
Tue, Oct 20, 2026+0+00Not trending
Wed, Oct 21, 2026+0+06Not trending
Thu, Oct 22, 2026+0+01Not trending
Fri, Oct 23, 2026+0+010Not trending
Sat, Oct 24, 2026+0+036#19
Sun, Oct 25, 2026+0+030#19
Mon, Oct 26, 2026+3+010#4
Tue, Oct 27, 2026+1+04#15
Wed, Oct 28, 2026+0+00Not trending
Thu, Oct 29, 2026+2+015#6
Fri, Oct 30, 2026+1+06Not trending
Sat, Oct 31, 2026+0+011#25
Sun, Nov 1, 2026+2+47#8
Mon, Nov 2, 2026+3+021#6
Tue, Nov 3, 2026+4+014#5
Wed, Nov 4, 2026+3+02#7
Thu, Nov 5, 2026+2+015#15
Fri, Nov 6, 2026+1+033#20
Sat, Nov 7, 2026+3+027#6
Sun, Nov 8, 2026+0+012Not trending
Mon, Nov 9, 2026+3+027#7
Tue, Nov 10, 2026+3+14#13
Wed, Nov 11, 2026+0+14Not trending
Thu, Nov 12, 2026+5+012#4
Fri, Nov 13, 2026+8+010#1
Sat, Nov 14, 2026+2+17#18
Sun, Nov 15, 2026+1+04Not trending
Mon, Nov 16, 2026+0+011Not trending
Tue, Nov 17, 2026+0+00Not trending
Wed, Nov 18, 2026+0+03Not trending
Thu, Nov 19, 2026+0+04Not trending
Fri, Nov 20, 2026+1+03Not trending
Total+65+16437
  • 1#1 on the list
  • 7Rank that day
  • Not trending
  • Mentions and achievements

    Where people are talking about kindlingai/gr8, and every badge it has earned
    1. Nov 41 post
      • Wow. Hitting nearly 2M downloads for kindlingai's exlr8 quants of GLM 5.3 and GLM 5.3 flash. Not just supported by gr8 ( but also @wrldsuksgo2mars's CuteAFD, @ashxhart's TensorFold and more.

        Read full on X, posted by @mmastrac

        @mmastrac · x.com

    2. Nov 21 post
      • We've really been pushing on multi-model support on gr8! Four DGX sparks, with three models to choose from. Each model is accelerated with EXLR8 - faster decode and lightning fast boot (< 30s!)

        Read full on X, posted by @mmastrac

        @mmastrac · x.com

    3. Nov 12 posts
      • Ready for EXLR8 for DeepSeek 4.1 flash? We've been cooking on some insane performance boosts for GLM 5.3 and GLM 5.3 flash too.

        Read full on X, posted by @mmastrac

        @mmastrac · x.com

      • It's an extension of GGUF just to encode the vectors so technically it should be fine:

        Read full on X, posted by @msuiche

        @msuiche · x.com

    4. Oct 311 post
      • Let's talk about steering vectors! (note: all of these examples below are real runs with GLM 5.3 on Most people think they're just for abliteration - ie removing refusals from a model to make it do…

        Read full on X, posted by @mmastrac

        @mmastrac · x.com

    5. 17 days earlier
    6. Oct 141 post
      • I'm doing some Ghidra based RE with GLM-5.3 Full on my 4 sparks and GLM-5.3-Flash as a worker on my Mac Studio tonight. 5.3 Full is noticeably smarter and more confident so far, coming to conclusions…

        Read full on X, posted by @JamesMcPherson

        @JamesMcPherson · x.com

    You might also like

    Repositories close to kindlingai/gr8
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    Busbar

    Control what AI can do before it acts

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks

    Python

    GLM-5.3 Flash EXL3 for 2-4x DGX Sparks

    762153

    Enntity/sparkglm

    Python

    Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.

    773

    MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold

    Python

    GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold

    535116

    MiaAI-Lab/GLM-5.3-Flash-DGX-Sparks-1104

    Shell

    GLM-5.3-Flash on DGX Sparks (ver 1104) with TensorFold

    15234

    HawkBearPig/dgpp

    C++

    Optimized inference for the DGX Spark and spark clusters

    14329

    alexellis/glm-5.3-flash-4x-dgx-spark-switchless

    Shell

    GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe

    11210

    tpurtell/ds41rt

    Rust

    Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers

    415

    bird/GLM-spark

    Python

    Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config and patches

    345

    MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks

    Shell

    GLM-5.2 NVFP4+AQLM on 3× DGX Spark — 380k context MTP serve stack

    729