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
Bifrost
Bifrost

NVIDIA/cutlass

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Visit GitHub
C++
10.7k
2k
261 contributors
Custom license
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

Momentum

How fast NVIDIA/cutlass 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

Sep 7 – Nov 6, 2026

Stars +317 in 61 days

051015
14

Forks +101 in 61 days

024
4

Merged PRs 19 in 61 days

024
4

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

Not in the Trendshift top 25 in this period

Sep 7Sep 15Sep 23Oct 1Oct 9Oct 17Oct 25Nov 2
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 PRs
Mon, Sep 7, 2026+13+00
Tue, Sep 8, 2026+4+21
Wed, Sep 9, 2026+3+40
Thu, Sep 10, 2026+7+00
Fri, Sep 11, 2026+1+40
Sat, Sep 12, 2026+8+20
Sun, Sep 13, 2026+3+10
Mon, Sep 14, 2026+5+30
Tue, Sep 15, 2026+8+10
Wed, Sep 16, 2026+6+20
Thu, Sep 17, 2026+4+11
Fri, Sep 18, 2026+5+30
Sat, Sep 19, 2026+5+40
Sun, Sep 20, 2026+3+00
Mon, Sep 21, 2026+2+20
Tue, Sep 22, 2026+4+31
Wed, Sep 23, 2026+11+14
Thu, Sep 24, 2026+9+10
Fri, Sep 25, 2026+7+20
Sat, Sep 26, 2026+4+20
Sun, Sep 27, 2026+2+10
Mon, Sep 28, 2026+2+10
Tue, Sep 29, 2026+7+10
Wed, Sep 30, 2026+5+00
Thu, Oct 1, 2026+3+30
Fri, Oct 2, 2026+2+20
Sat, Oct 3, 2026+2+00
Sun, Oct 4, 2026+4+20
Mon, Oct 5, 2026+8+00
Tue, Oct 6, 2026+4+20
Wed, Oct 7, 2026+8+10
Thu, Oct 8, 2026+1+20
Fri, Oct 9, 2026+3+00
Sat, Oct 10, 2026+5+20
Sun, Oct 11, 2026+3+10
Mon, Oct 12, 2026+5+03
Tue, Oct 13, 2026+10+32
Wed, Oct 14, 2026+8+21
Thu, Oct 15, 2026+11+31
Fri, Oct 16, 2026+14+20
Sat, Oct 17, 2026+8+00
Sun, Oct 18, 2026+5+20
Mon, Oct 19, 2026+4+00
Tue, Oct 20, 2026+11+22
Wed, Oct 21, 2026+9+30
Thu, Oct 22, 2026+2+00
Fri, Oct 23, 2026+4+30
Sat, Oct 24, 2026+4+10
Sun, Oct 25, 2026+4+20
Mon, Oct 26, 2026+4+10
Tue, Oct 27, 2026+6+20
Wed, Oct 28, 2026+1+21
Thu, Oct 29, 2026+8+10
Fri, Oct 30, 2026+3+20
Sat, Oct 31, 2026+3+00
Sun, Nov 1, 2026+3+30
Mon, Nov 2, 2026+6+20
Tue, Nov 3, 2026+2+20
Wed, Nov 4, 2026+2+31
Thu, Nov 5, 2026+3+41
Fri, Nov 6, 2026+6+00
Total+317+10119
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1

    • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Feb 20 – Jul 15, 2025Best #3

    #1#5#10#15#20#25
    Top 10
    Oct 2023AprOctAprOctAprOct
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about NVIDIA/cutlass, and every badge it has earned
    1. Aug 281 post

      • Hands on I am not sure how much value add I am, reading and thinking, prolly a bit

        Read full on X, posted by @lurker670291

        @lurker670291 · x.com

    2. Aug 271 post

      • Most developers try to write high-performance CUDA kernels or custom matrix multiplication routines from scratch and hope they hit peak hardware utilization. That approach usually fails. The better…

        Read full on X, posted by @Urooj978

        @Urooj978 · x.com

    3. 7 days earlier
    4. Aug 201 post

      • umm, yeah check it, i think there's defo a formulation here, it all boils down to tensor-products!

        Read full on X, posted by @PranshuBahadur

        @PranshuBahadur · x.com

    5. 8 days earlier
    6. Aug 121 post

      • btw CuTeDSL 4.7.0 introduced Task Scheduling (TS) kernels where instead of manually writing warp roles and sync barriers between them we declare and schedule them explicitly: - which resources are…

        Read full on X, posted by @maharshii

        @maharshii · x.com

    7. Aug 61 post

      • someone said it will be able to handle race condition statically which will be amazing

        Read full on X, posted by @henrylhtsang

        @henrylhtsang · x.com

    8. 16 days earlier
    9. Jul 211 post

      • Did you know how your name your kernels can change how they are compiled. There is some string matching behavior in the nvidia compilers that look for generated kernel names that begin with…

        Read full on X, posted by @SkyLi0n

        @SkyLi0n · x.com

    10. 22 days earlier
    11. Jun 291 post

      • 👀👀👀

        Read full on X, posted by @vikhyatk

        @vikhyatk · x.com

    12. 2 months earlier
    13. May 121 post

      • landed snake activation as an EVT op in CUTLASS for SM90 devices. PR #3184 merged into main. ~2.1x median speedup on Freya-TTS WaveGenerator, fusing the activation into the epilogue kills the extra…

        Read full on X, posted by @emre570_

        @emre570_ · x.com

    You might also like

    Repositories close to NVIDIA/cutlass
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

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

    NVIDIA/cudnn-frontend

    Python

    cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

    990334

    gau-nernst/gn-kernels

    Python
    494

    deepseek-ai/DeepGEMM

    Cuda

    DeepGEMM: clean and efficient BLAS kernel library on GPU

    9.2k1.4k

    HazyResearch/ThunderKittens

    Cuda

    Tile primitives for speedy kernels

    3.8k345

    NVIDIA/numba-cuda-mlir

    Python

    repo for Numba-CUDA-MLIR

    7540

    sgl-project/DeepGEMM

    Cuda

    DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

    4768

    Dao-AILab/quack

    Python

    A Quirky Assortment of CuTe Kernels

    1.2k178

    NVIDIA/cccl

    C++

    CUDA Core Compute Libraries

    2.6k567

    icl-utk-edu/magma

    Fortran
    12148