*quietly, sinking into chair* onnx is just protobuf github.com/onnx/onnx/bl...
github.com
November 30, 2024 at 3:33 PM
*quietly, sinking into chair* onnx is just protobuf github.com/onnx/onnx/bl...
ONNX is just protobuf? 🤯 mmapped.blog/posts/33-tra...
November 30, 2024 at 3:29 PM
ONNX is just protobuf? 🤯 mmapped.blog/posts/33-tra...
alright here's oculus lipsync (the plugin that most vtuber apps out there use) converted to an onnx file so that it can finally run natively on linux and silicon macs gitlab.com/veadotube/ov...
veadotube / ovrlipsync onnx · GitLab
lipsync plugin converted to an onnx model
gitlab.com
September 24, 2026 at 12:49 AM
alright here's oculus lipsync (the plugin that most vtuber apps out there use) converted to an onnx file so that it can finally run natively on linux and silicon macs gitlab.com/veadotube/ov...
For ${reasons} I’m having Claude draft a plan for Gemini to implement.
I’m amused that Claude is very clearly not open to Gemini’s opinions on its tech choices.
I’m amused that Claude is very clearly not open to Gemini’s opinions on its tech choices.
March 5, 2026 at 9:50 PM
For ${reasons} I’m having Claude draft a plan for Gemini to implement.
I’m amused that Claude is very clearly not open to Gemini’s opinions on its tech choices.
I’m amused that Claude is very clearly not open to Gemini’s opinions on its tech choices.
Why Java is the real production language for AI.
Python is ideal for experiments, but enterprise AI needs predictable concurrency, type safety, and stable runtimes. Java already gives us that, plus native performance through ONNX Runtime and Project Panama.
Read: buff.ly/0j6CZ8O
#Java #AI #ONNX
Python is ideal for experiments, but enterprise AI needs predictable concurrency, type safety, and stable runtimes. Java already gives us that, plus native performance through ONNX Runtime and Project Panama.
Read: buff.ly/0j6CZ8O
#Java #AI #ONNX
January 1, 2026 at 7:15 AM
Why Java is the real production language for AI.
Python is ideal for experiments, but enterprise AI needs predictable concurrency, type safety, and stable runtimes. Java already gives us that, plus native performance through ONNX Runtime and Project Panama.
Read: buff.ly/0j6CZ8O
#Java #AI #ONNX
Python is ideal for experiments, but enterprise AI needs predictable concurrency, type safety, and stable runtimes. Java already gives us that, plus native performance through ONNX Runtime and Project Panama.
Read: buff.ly/0j6CZ8O
#Java #AI #ONNX
GrapheneOS Speech Services version 3 released:
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36408-grap...
#GrapheneOS #privacy #security
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36408-grap...
#GrapheneOS #privacy #security
Release 3 · GrapheneOS/SpeechServices
Notable changes in version 3:
sync ONNX session close with runs to avoid upstream memory corruption bugs in ONNX
update Kotlin to 2.4.0
update detekt library to 2.0.0-alpha.4
update AndroidX Core ...
github.com
June 15, 2026 at 12:23 AM
GrapheneOS Speech Services version 3 released:
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36408-grap...
#GrapheneOS #privacy #security
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36408-grap...
#GrapheneOS #privacy #security
Turbocharge your AI! 🚀 Learn how to maximize ONNX performance on dedicated servers for lightning-fast speeds.
If you want to see the coding part, view the full tutorial on our website:
👉 www.ctcservers.com/tutorials/ho...
#AI #MachineLearning #ONNX #ServerOptimization #Python
If you want to see the coding part, view the full tutorial on our website:
👉 www.ctcservers.com/tutorials/ho...
#AI #MachineLearning #ONNX #ServerOptimization #Python
October 2, 2026 at 4:31 AM
Turbocharge your AI! 🚀 Learn how to maximize ONNX performance on dedicated servers for lightning-fast speeds.
If you want to see the coding part, view the full tutorial on our website:
👉 www.ctcservers.com/tutorials/ho...
#AI #MachineLearning #ONNX #ServerOptimization #Python
If you want to see the coding part, view the full tutorial on our website:
👉 www.ctcservers.com/tutorials/ho...
#AI #MachineLearning #ONNX #ServerOptimization #Python
ONNX คืออะไร
อ่านต่อ : www.blockdit.com/posts/6a47c8...
#ShoperGamer #ONNX #ONNXRuntime #ML #DL #Opensource #Performance #Ai #Knowledge #Study #Feed
อ่านต่อ : www.blockdit.com/posts/6a47c8...
#ShoperGamer #ONNX #ONNXRuntime #ML #DL #Opensource #Performance #Ai #Knowledge #Study #Feed
July 4, 2026 at 5:31 AM
ONNX คืออะไร
อ่านต่อ : www.blockdit.com/posts/6a47c8...
#ShoperGamer #ONNX #ONNXRuntime #ML #DL #Opensource #Performance #Ai #Knowledge #Study #Feed
อ่านต่อ : www.blockdit.com/posts/6a47c8...
#ShoperGamer #ONNX #ONNXRuntime #ML #DL #Opensource #Performance #Ai #Knowledge #Study #Feed
got pose estimation going on cpu now using ONNX YOLO v8n... but it can only detect poses from photos and videos of real or realistic people 🥹
trying out different captioning models, here's llama joycaption vs moondream v3, im leaning towards joycaption although... it took like 3 mins to caption a single image on my cpu 🥲
October 2, 2025 at 12:40 PM
got pose estimation going on cpu now using ONNX YOLO v8n... but it can only detect poses from photos and videos of real or realistic people 🥹
From Jev to Your Laptop: Building "System One" Decision Models in ONNX with Mobius #machinelearning #ai
From Jev to Your Laptop: Building "System One" Decision Models in ONNX with Mobius
Groups
Conversations
All groups and messages
Sign in
Machine Learning, Deep Learning and AI
Conversations
About
Privacy • Terms
From Jev to Your Laptop: Building "System One" Decision Models in ONNX with Mobius
0 views
Skip to first unread message
Eyal Estrin
unread,
8:27 PM (16 minutes ago)
to
https://techcommunity.microsoft.com/blog/azuredevcommunityblog/from-jev-to-your-laptop-building-system-one-decision-models-in-onnx-with-mobius/4558843
Eyal Estrin
Author | Cloud Architect | AWS • Azure • GCP Insights
Social: @eyalestrin
Connect: https://linktr.ee/eyalestrin Blog: https://security-24-7.com
Reply all
Reply to author
Forward
dlvr.it
October 2, 2026 at 3:42 AM
From Jev to Your Laptop: Building "System One" Decision Models in ONNX with Mobius #machinelearning #ai
Luff the yuo backed Onnx 🧡
September 11, 2025 at 10:09 PM
Luff the yuo backed Onnx 🧡
GrapheneOS Speech Services version 2 released:
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36001-grap...
#GrapheneOS #privacy #security
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36001-grap...
#GrapheneOS #privacy #security
Release 2 · GrapheneOS/SpeechServices
Notable changes in version 2:
switch to ABI specific APKs (reduces APK size from 162MB to 76MB for 64-bit ARM)
fix ONNX resource leaks and refactor usages of ONNX APIs
handle null TTS voice name t...
github.com
June 1, 2026 at 6:02 PM
GrapheneOS Speech Services version 2 released:
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36001-grap...
#GrapheneOS #privacy #security
github.com/GrapheneOS/S...
See the linked release notes for a summary of the improvements over the previous release and a link to the full changelog.
Forum discussion thread:
discuss.grapheneos.org/d/36001-grap...
#GrapheneOS #privacy #security
Finally got XBlock-M quantized and exported to Onnx ✨
Tomorrow I integrate it into the autolabeller and hopefully it goes online for the first time!
Tomorrow I integrate it into the autolabeller and hopefully it goes online for the first time!
October 16, 2024 at 1:25 AM
Finally got XBlock-M quantized and exported to Onnx ✨
Tomorrow I integrate it into the autolabeller and hopefully it goes online for the first time!
Tomorrow I integrate it into the autolabeller and hopefully it goes online for the first time!
TTS (text-to-speech) Model that runs on a CPU (open-weight)
Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.
huggingface.co/Supertone/su...
Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.
huggingface.co/Supertone/su...
May 16, 2026 at 8:15 PM
TTS (text-to-speech) Model that runs on a CPU (open-weight)
Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.
huggingface.co/Supertone/su...
Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.
huggingface.co/Supertone/su...
📢 New #updates · 29 Sept #7.1
· librephotos 1.2.0 — Machine learning models now run on ONNX Runtime
· VueTorrent v2.36.0 — RSS feeds and category form fixes
· librephotos 1.2.0 — Machine learning models now run on ONNX Runtime
· VueTorrent v2.36.0 — RSS feeds and category form fixes
September 29, 2026 at 8:19 AM
📢 New #updates · 29 Sept #7.1
· librephotos 1.2.0 — Machine learning models now run on ONNX Runtime
· VueTorrent v2.36.0 — RSS feeds and category form fixes
· librephotos 1.2.0 — Machine learning models now run on ONNX Runtime
· VueTorrent v2.36.0 — RSS feeds and category form fixes
OpenCV 5.0 debuts a new DNN engine, broader ONNX support, VLM inference, C++17 requirements, and legacy API cleanup.
linuxiac.com/opencv-5-0-c...
#OpenSource
linuxiac.com/opencv-5-0-c...
#OpenSource
OpenCV 5.0 Computer Vision Library Released with Rewritten DNN Engine
OpenCV 5.0 debuts a new DNN engine, broader ONNX support, VLM inference, C++17 requirements, and legacy API cleanup.
linuxiac.com
June 8, 2026 at 3:49 PM
OpenCV 5.0 debuts a new DNN engine, broader ONNX support, VLM inference, C++17 requirements, and legacy API cleanup.
linuxiac.com/opencv-5-0-c...
#OpenSource
linuxiac.com/opencv-5-0-c...
#OpenSource
Anyone can cook.
Now anyone can cut out a background in #rstats.
rembg is on CRAN via ONNX and the onnxr package.
png::writePNG(rembg("remy.jpg"), "remy_rembg.png")
cran.r-project.org/web/packages...
Now anyone can cut out a background in #rstats.
rembg is on CRAN via ONNX and the onnxr package.
png::writePNG(rembg("remy.jpg"), "remy_rembg.png")
cran.r-project.org/web/packages...
July 22, 2026 at 4:29 PM
Anyone can cook.
Now anyone can cut out a background in #rstats.
rembg is on CRAN via ONNX and the onnxr package.
png::writePNG(rembg("remy.jpg"), "remy_rembg.png")
cran.r-project.org/web/packages...
Now anyone can cut out a background in #rstats.
rembg is on CRAN via ONNX and the onnxr package.
png::writePNG(rembg("remy.jpg"), "remy_rembg.png")
cran.r-project.org/web/packages...
i’m glad i’m in a positive mental space right now because onnx is really trying its best to crush my spirits
November 22, 2024 at 5:44 AM
i’m glad i’m in a positive mental space right now because onnx is really trying its best to crush my spirits
New in Stable-Baselines3 documentation: a full example on how to export a trained RL agent to run in the browser, using ONNX and ONNX Runtime Web (JS).
Demo: jonathancoletti.github.io/CarDodgingGym/
Documentation: stable-baselines3.readthedocs.io/en/master/gu...
Demo: jonathancoletti.github.io/CarDodgingGym/
Documentation: stable-baselines3.readthedocs.io/en/master/gu...
December 5, 2025 at 5:39 PM
New in Stable-Baselines3 documentation: a full example on how to export a trained RL agent to run in the browser, using ONNX and ONNX Runtime Web (JS).
Demo: jonathancoletti.github.io/CarDodgingGym/
Documentation: stable-baselines3.readthedocs.io/en/master/gu...
Demo: jonathancoletti.github.io/CarDodgingGym/
Documentation: stable-baselines3.readthedocs.io/en/master/gu...
Supertonic est un projet open-source sous licences MIT, permettant de générer localement, via ONNX Runtime, de la synthèse vocale multilingue en 31 langues, sans service cloud ⬇️
github.com/supertone-in...
github.com/supertone-in...
GitHub - supertone-inc/supertonic: Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX. - supertone-inc/supertonic
github.com
May 19, 2026 at 6:01 AM
Supertonic est un projet open-source sous licences MIT, permettant de générer localement, via ONNX Runtime, de la synthèse vocale multilingue en 31 langues, sans service cloud ⬇️
github.com/supertone-in...
github.com/supertone-in...
Released BodyPixSentis v5.0.0 for Unity 6. Migrated the pre/post-processing shaders to a functional graph, and switched from .onnx to baked .sentis files. github.com/keijiro/Body...
February 28, 2026 at 9:35 AM
Released BodyPixSentis v5.0.0 for Unity 6. Migrated the pre/post-processing shaders to a functional graph, and switched from .onnx to baked .sentis files. github.com/keijiro/Body...
Microsoft seizes 240 websites used by Egyptian phishing-as-a-service operation ‘ONNX’, therecord.media/microsoft-se...
Microsoft seizes 240 websites used by Egyptian phishing-as-a-service operation ‘ONNX’
Microsoft and LF Projects sued Abanoub Nady and four unidentified people for running ONNX, a key player in the phishing-as-a-service industry.
therecord.media
November 22, 2024 at 10:29 AM
Microsoft seizes 240 websites used by Egyptian phishing-as-a-service operation ‘ONNX’, therecord.media/microsoft-se...
inference4j: Java Inference API for Onnx models. Run AI models in Java. Three lines of code, zero setup.
#ai #inference #java #models #onnx
github.com/inference4j/...
#ai #inference #java #models #onnx
github.com/inference4j/...
GitHub - inference4j/inference4j: Java Inference API for Onnx models
Java Inference API for Onnx models. Contribute to inference4j/inference4j development by creating an account on GitHub.
github.com
February 24, 2026 at 10:42 PM
inference4j: Java Inference API for Onnx models. Run AI models in Java. Three lines of code, zero setup.
#ai #inference #java #models #onnx
github.com/inference4j/...
#ai #inference #java #models #onnx
github.com/inference4j/...
🚀 Unlock blazing-fast neural network inference on AMD hardware!
Discover how to maximize #ONNX Runtime + #DirectML with DirectX 12 for seamless GPU pipelines.
🛠️ Dive into practical setup tips and code samples in our latest guide: gpuopen.com/learn/onnx-d...
Discover how to maximize #ONNX Runtime + #DirectML with DirectX 12 for seamless GPU pipelines.
🛠️ Dive into practical setup tips and code samples in our latest guide: gpuopen.com/learn/onnx-d...
ONNX and DirectML execution provider guide - part 1 - AMD GPUOpen
Learn how to optimize neural network inference on AMD hardware using the ONNX Runtime with the DirectML execution provider and DirectX 12 in the first part of our guide.
gpuopen.com
October 31, 2025 at 8:58 PM
🚀 Unlock blazing-fast neural network inference on AMD hardware!
Discover how to maximize #ONNX Runtime + #DirectML with DirectX 12 for seamless GPU pipelines.
🛠️ Dive into practical setup tips and code samples in our latest guide: gpuopen.com/learn/onnx-d...
Discover how to maximize #ONNX Runtime + #DirectML with DirectX 12 for seamless GPU pipelines.
🛠️ Dive into practical setup tips and code samples in our latest guide: gpuopen.com/learn/onnx-d...
I've been working towards implementing a number of onnx computer vision models directly in TouchDesigner. It's wild how much python I'm writing these days.
This is DepthAnythingV2 running at 60fps with a 256x256 input. ~10ms inference time on a laptop 4090 🤯
This is DepthAnythingV2 running at 60fps with a 256x256 input. ~10ms inference time on a laptop 4090 🤯
July 15, 2025 at 1:26 PM
I've been working towards implementing a number of onnx computer vision models directly in TouchDesigner. It's wild how much python I'm writing these days.
This is DepthAnythingV2 running at 60fps with a 256x256 input. ~10ms inference time on a laptop 4090 🤯
This is DepthAnythingV2 running at 60fps with a 256x256 input. ~10ms inference time on a laptop 4090 🤯