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

microsoft/onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Visit GitHub
C++
22.3k
4.3k
933 contributors
MIT 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 microsoft/onnxruntime 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 +483 in 61 days

0102030
21

Forks +222 in 61 days

0510
9

Merged PRs 755 in 61 days

02040
37

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+20+20
Tue, Sep 8, 2026+4+39
Wed, Sep 9, 2026+8+426
Thu, Sep 10, 2026+12+111
Fri, Sep 11, 2026+11+410
Sat, Sep 12, 2026+9+30
Sun, Sep 13, 2026+4+31
Mon, Sep 14, 2026+11+56
Tue, Sep 15, 2026+5+115
Wed, Sep 16, 2026+10+37
Thu, Sep 17, 2026+9+127
Fri, Sep 18, 2026+14+211
Sat, Sep 19, 2026+5+23
Sun, Sep 20, 2026+5+40
Mon, Sep 21, 2026+3+37
Tue, Sep 22, 2026+6+426
Wed, Sep 23, 2026+11+513
Thu, Sep 24, 2026+10+212
Fri, Sep 25, 2026+5+315
Sat, Sep 26, 2026+0+14
Sun, Sep 27, 2026+3+31
Mon, Sep 28, 2026+8+510
Tue, Sep 29, 2026+8+410
Wed, Sep 30, 2026+14+426
Thu, Oct 1, 2026+11+325
Fri, Oct 2, 2026+6+319
Sat, Oct 3, 2026+18+312
Sun, Oct 4, 2026+9+31
Mon, Oct 5, 2026+13+425
Tue, Oct 6, 2026+4+123
Wed, Oct 7, 2026+7+419
Thu, Oct 8, 2026+5+137
Fri, Oct 9, 2026+4+515
Sat, Oct 10, 2026+8+36
Sun, Oct 11, 2026+1+51
Mon, Oct 12, 2026+8+68
Tue, Oct 13, 2026+13+48
Wed, Oct 14, 2026+9+811
Thu, Oct 15, 2026+6+412
Fri, Oct 16, 2026+14+413
Sat, Oct 17, 2026+6+65
Sun, Oct 18, 2026+8+32
Mon, Oct 19, 2026+4+610
Tue, Oct 20, 2026+4+611
Wed, Oct 21, 2026+9+117
Thu, Oct 22, 2026+12+916
Fri, Oct 23, 2026+9+515
Sat, Oct 24, 2026+9+11
Sun, Oct 25, 2026+10+31
Mon, Oct 26, 2026+4+915
Tue, Oct 27, 2026+6+315
Wed, Oct 28, 2026+4+324
Thu, Oct 29, 2026+3+327
Fri, Oct 30, 2026+6+619
Sat, Oct 31, 2026+6+26
Sun, Nov 1, 2026+9+23
Mon, Nov 2, 2026+3+318
Tue, Nov 3, 2026+5+430
Wed, Nov 4, 2026+8+715
Thu, Nov 5, 2026+21+620
Fri, Nov 6, 2026+6+10
Total+483+222755
  • 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

    Oct 8, 2023 – Aug 21, 2026Best #12

    #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 microsoft/onnxruntime, and every badge it has earned
    1. Nov 51 post

      • On Oct 20 I spent 27 minutes installing torch just to embed 5 sentences. Today I ran the exact same model with zero torch. 25 seconds, start to finish. Same model: all-MiniLM-L6-v2, 384-dim. Same 5…

        Read full on X, posted by @ReignSwords

        @ReignSwords · x.com

    2. Oct 311 post

      • @SparkLLM's new 4B model running entirely in the browser. Thinking mode, tool calls, 16k context, about 85 tok/s on a 3090 Ti. No server, nothing to install, and nothing you type leaves your machine.

        Read full on X, posted by @MohdMahmodi

        @MohdMahmodi · x.com

    3. 24 days earlier
    4. Oct 71 post

      • Your model runs on one device. Production models need to run everywhere—CPU, GPU, TPU, edge. ONNX Runtime abstracts that so you don't rewrite.

        Read full on X, posted by @Crashlandenx

        @Crashlandenx · x.com

    5. 19 days earlier
    6. Sep 181 post

      • Microsoft spent millions building their AI stack. Then they dumped all of it on GitHub. For free. Most engineers have no clue these exist. 10 repos that teach agents, RAG, and model deployment better…

        Read full on X, posted by @BuiltByNav

        @BuiltByNav · x.com

    7. 24 days earlier
    8. Aug 251 post

      • AI models look great in a Jupyter notebook, but they often struggle with high latency and heavy memory bloat in production. Microsoft built an open-source engine specifically to solve this. It is…

        Read full on X, posted by @Urooj978

        @Urooj978 · x.com

    9. Aug 221 post

      • 微软开源的推理加速引擎 ONNX Runtime，跨平台、高性能，把你训练好的模型塞进去，它负责让推理飞起来 🚀 C++ 内核，21k Star 不是盖的。

        Read full on X, posted by @bookingX0

        @bookingX0 · x.com

    10. 2 months earlier
    11. Jun 121 post

      • ONNX Runtime turns LLMs into true deployment assets. It's not just about faster inference; it's about unifying PyTorch, TensorFlow, scikit-learn models on diverse hardware, a critical step for…

        Read full on X, posted by @dmshirochenko

        @dmshirochenko · x.com

    You might also like

    Repositories close to microsoft/onnxruntime
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

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

    ROCm/AMDMIGraphX

    C++

    AMD's graph optimization engine.

    338162

    google/jaxonnxruntime

    Python

    A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.

    13829

    pytorch/TensorRT

    Python

    PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

    3k419

    luminal-ai/luminal

    Rust

    Inference at the speed of light.

    3k258

    google-ai-edge/ml-drift

    C++

    GPU-Accelerated AI/ML Inference

    24629

    zml/zml

    Zig

    Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

    4.2k203

    pykeio/ort

    Rust

    Fast ML inference & training for ONNX models in Rust

    2.6k261

    vitoplantamura/OnnxStream

    C++

    Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK. Python, C# and JS(WASM) bindings available.

    2.1k100

    google-ai-edge/LiteRT

    C++

    LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

    3.6k501