onnxruntime
quickadd
onnxruntime | quickadd | |
---|---|---|
54 | 38 | |
12,736 | 188 | |
2.7% | -0.5% | |
10.0 | 5.3 | |
7 days ago | about 2 months ago | |
C++ | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
onnxruntime
-
Machine Learning with PHP
ONNX Runtime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
-
AI Inference now available in Supabase Edge Functions
Embedding generation uses the ONNX runtime under the hood. This is a cross-platform inferencing library that supports multiple execution providers from CPU to specialized GPUs.
-
Deep Learning in JavaScript
tfjs is dead, looking at the commit history. The standard now is to convert PyTorch to onnx, then use onnxruntime (https://github.com/microsoft/onnxruntime/tree/main/js/web) to run the model on the browsdr.
- FLaNK Stack 05 Feb 2024
-
Vcc – The Vulkan Clang Compiler
- slang[2] has the potential, but the meta programming part is not as strong as C++, existing libraries cannot be used.
The above conclusion is drawn from my work https://github.com/microsoft/onnxruntime/tree/dev/opencl, purely nightmare to work with thoes drivers and jit compilers. Hopefully Vcc can take compute shader more seriously.
[1]: https://www.circle-lang.org/
-
Oracle-samples/sd4j: Stable Diffusion pipeline in Java using ONNX Runtime
I did. It depends what you want, for an overview of how ONNX Runtime works then Microsoft have a bunch of things on https://onnxruntime.ai, but the Java content is a bit lacking on there as I've not had time to write much. Eventually I'll probably write something similar to the C# SD tutorial they have on there but for the Java API.
For writing ONNX models from Java we added an ONNX export system to Tribuo in 2022 which can be used by anything on the JVM to export ONNX models in an easier way than writing a protobuf directly. Tribuo doesn't have full coverage of the ONNX spec, but we're happy to accept PRs to expand it, otherwise it'll fill out as we need it.
- Mamba-Chat: A Chat LLM based on State Space Models
-
VectorDB: Vector Database Built by Kagi Search
What about models besides GPT? Most of the popular vector encoding models aren't using this architecture.
If you really didn't want PyTorch/Transformers, you could consider exporting your models to ONNX (https://github.com/microsoft/onnxruntime).
- ONNX runtime: Cross-platform accelerated machine learning
- Onnx Runtime: “Cross-Platform Accelerated Machine Learning”
quickadd
- Ship Faster by Organising Less
-
From a Day to 17 Minutes: How We’ve Dealt with Slow Build Times
by Adam Pavlisin & Slavo Glinsky ➤➤➤ https://acreom.com
-
My productivity app is a never-ending .txt file
there's a much better way providing simplicity with full data ownership and real tasks out of the box in daily documents https://acreom.com
-
100% User-Supported
the premise of this article is false. acreom [1] is VC backed, and doesn’t implement any of the mentioned practices. No price subsidising (quite the opposite), no pressure to create lock-in or monetize user data etc. There’s nothing wrong with being VC backed given the expectations between investors, the team and users are aligned.
[1] https://acreom.com/
-
Skiff is shutting down in six months
Check out https://acreom.com, you literally own the software, it's local-first, E2EE, integrated, runs on markdown files, and once you download the app you can keep it forever.
-
Show HN: Find consistent and conflict-free shortcuts for your app
Hello HN! Maker of Keycheck.dev here.
Keycheck is an open-source web app that lets you quickly find consistent and conflict-free shortcuts for your app. Currently featuring over 100 apps, and 1400 shortcuts.
When designing keyboard shortcuts for our main app - acreom (https://acreom.com/), we wanted to create a great keyboard user experience. This involves designing shortcuts which are easy to hit, easy to remember, and do not clash with the system shortcuts. We have learned that there’s no reason to reinvent the wheel and it’s easier to follow conventions from other popular apps to achieve this. Finding this out, however, was frustrating, and involved lots of manual work of downloading and signing in to other apps.
We decided to solve this problem and open-source our solution to help other makers in the process of designing shortcuts. You can match any key combination against combinations of other apps, search shortcuts by their keybinds, descriptions, or by app, and explore the apps and see their shortcuts. Feel free to play around and explore all the possibilities.
The code is fully open-sourced (https://github.com/Acreom/keycheck) and contributions are welcome! If you are a maker, feel free add your app to help other makers and increase visibility for your own project.
Looking forward to the feedback!
-
A CEO's Guide to Emacs
with the steep learning curve of setting it up followed by the never ending UX complexities emacs seems like it's for people who get satisfaction of spending time setting things up rather than being effective. A modern alternative of this is Notion.
On the contrary, for people who care about getting stuff done with a capture-first organize-later interface that works out of the box like an iPhone, options are limited.
for the curious ones I'm building one myself https://acreom.com
- Welche Note taking/Wiki App nutzt ihr, falls überhaupt?
-
Created a versus list for Note Taking Apps (last tab). What do you guys think? Did I miss anything?
- acreom (https://acreom.com)
-
Ask HN: Who is hiring? (July 2023)
acreom | DevRel (remote) or Prague (Czechia)
https://acreom.com is a markdown knowledge base with tasks for developers. We're building a delightful and integrated interface developers love using alongside their code editors to organise their work.
reach out to me directly /martin at acreom dot com/ for more info.
What are some alternatives?
onnx - Open standard for machine learning interoperability
roqr - QR codes that will rock your world
onnx-tensorrt - ONNX-TensorRT: TensorRT backend for ONNX
markwhen - Make a cascading timeline from markdown-like text. Supports simple American/European date styles, ISO8601, images, links, locations, and more.
onnx-simplifier - Simplify your onnx model
chrono - A natural language date parser in Javascript
ONNX-YOLOv7-Object-Detection - Python scripts performing object detection using the YOLOv7 model in ONNX.
notebook - Tool for Thought. ʚɞ
onnx-tensorflow - Tensorflow Backend for ONNX
notes
MLflow - Open source platform for the machine learning lifecycle
notable - The Markdown-based note-taking app that doesn't suck.