Re:Microsoft's ONNX Runtime has disappeared from GitHub
by nvader on Tuesday November 17, 2026 @06:24PM
(#50539658)
We found out about this this morning, when evals started failing in our pipelines. I've been looking around, but it doesn't seem like there was any advance warning about this.
Does anyone know why or how a repository with 22k stars just went dark?
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by robjam on Tuesday November 17, 2026 @07:04PM
(#50540064)
That would be my guess also. About 6 months ago the azure-functions-host repo disappeared for a while (I got a concerning automated email from GitHub from my forked repo citing a ToS violation).
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by quietbritishjim on Tuesday November 17, 2026 @07:58PM
(#50540489)
If I understand your implication, that's not what "supply chain attack" normally means. That term means attacking the mechanism that delivers your packages to deliver a different, more compromised, package. If the package itself is already compromised then that's just a straightforward dependency vulnerability.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by giancarlostoro on Tuesday November 17, 2026 @08:33PM
(#50540746)
Considering Microsoft co-developed ONNX with Facebook... I think that the more likely scenario is they took it dark after learning that it has security issues, but they should really have left a message or something, this is amateur hour tier. GitHub repos should let you leave a "Sorry we've hidden our repo, we learned about security issues" which kind of doesn't help anyone either... since now they have to find help elsewhere, and fall victim to sketchy 'forks' from other people...
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by nicelunch on Tuesday November 17, 2026 @07:00PM
(#50540021)
I checked my own github account and surprised to find that I had no repositories at all, I have deleted none. There may be a temporary outage with Github as well?
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by momojo on Tuesday November 17, 2026 @07:47PM
(#50540401)
> The ONNX Runtime (ORT) is the most widely used engine for serving deep
learning models in production. It is common for people to download ONNX
models from public repositories, such as Hugging Face, and to serve them to
their customers without too much scrutiny. In March 2026, we noticed a
parser flaw: an ONNX model can cause ORT to read from arbitrary file paths
(or memory addresses) without validations.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by katbyte on Tuesday November 17, 2026 @10:37PM
(#50541545)
No that’s forking, vendoring usually means keeping a local copy of a library in /vendor that is automatically committed - rust and golang have first class support for this
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by rtpg on Tuesday November 17, 2026 @08:59PM
(#50540942)
I do wish I could pay some money for a package manager intermediary that "magically" handles things (for example defaulting to not promoting things until 2 weeks have passed), has better perf, and generally just does the right things.
Of course I wouldn't pay _that_ much money for it.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by pjmlp on Wednesday November 18, 2026 @01:01AM
(#50542414)
I don't get it, this is exactly how I have been mostly working since around 2010.
Nothing that lands on CI/CD pipelines is able to download anything directly from Internet, rather internal repos based on Nexus, Artfactory and similar.
Additionally everything that gets uploaded into them needs to have an approval process for the most part.
So, not only already exists, it is an intermediate process, and you can even pay depending on the features.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by kreco on Wednesday November 18, 2026 @06:19AM
(#50544900)
It baffles me that this is not the default.
I mean, sure for hobby project you don't want to setup/pay some intermediate repos.
But for anything else you just want control, if new version of an app is released, someone needs to actively bring it to the intermediate repository.
This is tangential, but that's also why being able to import a package from a git url in some language is extremely risky (your github repo could change owners at any time).
At least the code should only know about the package id, and whatever "package manager" is install should link it to a repository.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by malikolivier on Wednesday November 18, 2026 @02:55AM
(#50543140)
Such solutions exist. Some people are building it on their own. Some people just commit all their dependencies in their repository.
If you want it enforced for a whole team, with caching on top, that's
where registry proxies come in (Artifactory, Nexus, and similar). The big
ones take real effort to set up, while lighter ones may be all you need.
Vendoring your dependencies into the repo is the low-tech option that survives an upstream repo vanishing.
Disclosure: I work at a company which sell such solutions.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by UncleOxidant on Tuesday November 17, 2026 @08:12PM
(#50540605)
Aren't there other ONNX runtimes out there? A quick google search shows a few written in Rust: Tract, RTen, WONNX, Burn&Candle. Also, IIRC there's a Julia-based one as well.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by ytxm on Tuesday November 17, 2026 @08:35PM
(#50540756)
Have used it with wasm and it's lovely, but I was kindof disappointed to learn internally it's basically another serialisation format. I imagined gigabytes of generated Rust code hehe
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by antimora on Tuesday November 17, 2026 @09:05PM
(#50540975)
The graph is converted into Rust code that calls Burn APIs but the weights are converted into Burn's format, called burnpack (similar to safetensors but instead of JSON we use CBOR for weights meta data).
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by robertknight on Wednesday November 18, 2026 @04:30AM
(#50543994)
I maintain RTen (https://github.com/robertknight/rten). It is a good drop-in replacement for ONNX Runtime for many use cases where you are running inference on CPU (there is no GPU support yet). There is no Python or NodeJS API at present, though you could get an agent to build a small wrapper quite easily.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by robjam on Wednesday November 18, 2026 @04:39AM
(#50544082)
I've used your library ocr to read serial numbers on an IoT device on a mobile phone. It was really responsive and faster than tesseractjs in a web worker. Just wanted to say thanks for such well thought software!
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by coffee_am on Wednesday November 18, 2026 @10:45AM
(#50547718)
Yet another alternative: convert your `.onnx` file to GoMLX [0] using onnx-gomlx [1].
For CPUs using SIMD it's significantly faster than ONNX. For NVidia GPUs, depending on the model, you can use an XLA backend. On Apple you can use an MLX backend (but it supports Neon/SME as well).
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by eddythompson80 on Tuesday November 17, 2026 @08:13PM
(#50540608)
FYI - ONNX will automatically exfiltrate data about your application with no way to opt out other than building it from source with telemetry disabled. Maybe you could block DNS too.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by ctrlkctrls on Wednesday November 18, 2026 @02:05AM
(#50542827)
I don't see the connection you're implying? What has ham radio got to do with any of this? There's nothing secret or being exfil'd in ham radio since it's all unencrypted and transmitted on public airwaves. In the USA anyway. I'm not sure what other licensing authorities in other countries allow.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by refulgentis on Wednesday November 18, 2026 @12:42AM
(#50542309)
I don’t understand what you mean. I’ve maintained a decently popular ONNX wrapper for years, had 0 idea there was telemetry, and this is quite useful info to have, particularly because it would be a PITA to rebuild binaries right now.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by extrano84 on Wednesday November 18, 2026 @12:09PM
(#50548903)
I only found out ONNX had telemetry because one time my program (that uses it) out of nowhere started hanging on closing.
Looking at the command line output I realised it was because ONNX telemetry couldn't connect to their server and it just kept retrying the connection.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by refulgentis on Wednesday November 18, 2026 @03:36PM
(#50551789)
Good lord.
I was doing a Dart wrapper for MXC* this week, and found it was doing telemetry, though IIRC it was forthrightly/clearly documented.
Been on this planet long enough that I've seen plenty of MBAs saying "hoover every piece of data every time we can" and eng going along without thinking or saying anything.
I'm still somewhat surprised Microsoft would do that in SDKs.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by snnn on Thursday November 19, 2026 @12:16AM
(#50556333)
Previous developer here. To clarify, ONNX and ONNX Runtime are two different things. ONNX Runtime is a Microsoft project while ONNX is community owned. Previously ONNX Runtime collected telemetry for their Windows users that use the prebuilt binaries from Microsoft. No data collection for non-Windows cases.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by snnn on Thursday November 19, 2026 @12:12AM
(#50556306)
Previous developer here. Previously there was a bug preventing it working as expected. Someone reported the issue to us via Github issues. If the repo is still alive, you can check the issue and code. ONNX Runtime is almost fully open source. You can audit the code. Before I left, I can say for sure that if you build everything from source there would be no telemetry. However, Windows itself may still collect data, which is a separated and large topic.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by gbdubs on Wednesday November 18, 2026 @11:33AM
(#50548375)
I don't think this is true, with an env var of `ORT_DISABLE_TELEMETRY=1 stops sending telemetry on all of the builds I tested.
The flag/telemetry client doesn't exist on v1.28.0, and when I tested on v1.29.0, v1.30.0, v1.31.0, v1.31.1 and v1.32.0 running on MacOS, all built from source locally at those various checkpoints, I don't see the any of the telemetry infrastructure built (device ID is unset, no network queue created, no network session storage created).
Could you provide more context on what the issue here was/is? I might be missing it.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by craigacp on Tuesday November 17, 2026 @08:59PM
(#50540943)
How odd. https://onnxruntime.ai is still up, and the packages still appear to be on PyPI, Maven Central etc. Guess I won't submit the PR I was working on tonight then.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by snnn on Thursday November 19, 2026 @12:35AM
(#50556428)
Thank you so much for your years of dedication and contributions to ONNX Runtime Java! We truly appreciate all the time and effort you've put into making ONNX Runtime Java better!
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by these on Tuesday November 17, 2026 @09:36PM
(#50541146)
Not to take away from the fact that I don't like that this was done, but in my experience development on ONNX has been pretty slow recently. I moved away from a few months back because I felt bug fixes were coming in pretty slow, despite being reported.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by these on Wednesday November 18, 2026 @02:16PM
(#50550715)
I've switched over to Candle. I quite like it so far, and its significantly reduced my app size while having the same speed. The compiled nature of it means you need to implement your model in a pytorch-like API, but the compiler removes all unused ops which was a pain to do in onnxruntime.
Re:Microsoft's ONNX Runtime has disappeared from GitHub
by Gluber on Tuesday November 17, 2026 @11:46PM
(#50541981)
It seemed to have stalled in investment before i think. Performance especially for CPU only models ( there are some use cases for this ) seemed to have lagged a lot, behind what properly hand optimized code could do.
The gpu work was mostly handed of e.g to TensorRT and that also seems since the push for more general LLM models have not really improved.
Does anyone know why or how a repository with 22k stars just went dark?
[0]: https://phrack.org/issues/73/backdoor-attacks-against-machin...
Almost everything seems exploitable, and a sandbox adds at least one more layer of protection against those attacks.
https://github.com/ashishb/amazing-sandbox
Source: https://opensourcemalware.com/blog/agent-framework-pypi-comp...
You never know when it's going to vanish
Of course I wouldn't pay _that_ much money for it.
Though I'm pretty sure their enterprise pricing is "give us a call." Maybe your last sentence was a nod to this.
Nothing that lands on CI/CD pipelines is able to download anything directly from Internet, rather internal repos based on Nexus, Artfactory and similar.
Additionally everything that gets uploaded into them needs to have an approval process for the most part.
So, not only already exists, it is an intermediate process, and you can even pay depending on the features.
I mean, sure for hobby project you don't want to setup/pay some intermediate repos.
But for anything else you just want control, if new version of an app is released, someone needs to actively bring it to the intermediate repository.
This is tangential, but that's also why being able to import a package from a git url in some language is extremely risky (your github repo could change owners at any time). At least the code should only know about the package id, and whatever "package manager" is install should link it to a repository.
If you want it enforced for a whole team, with caching on top, that's where registry proxies come in (Artifactory, Nexus, and similar). The big ones take real effort to set up, while lighter ones may be all you need.
Vendoring your dependencies into the repo is the low-tech option that survives an upstream repo vanishing.
Disclosure: I work at a company which sell such solutions.
> https://github.com/syntax-syndicate/onnxruntime
Check the web archive link for commit hashes, the syntax-syndicate fork seems to be the remaining legit fork.
[1] https://web.archive.org/web/20261113082932/https://github.co...
I maintain this project at the moment.
It convert ONNX models into native, backend-agnostic Burn code for inference and fine-tuning.
For CPUs using SIMD it's significantly faster than ONNX. For NVidia GPUs, depending on the model, you can use an XLA backend. On Apple you can use an MLX backend (but it supports Neon/SME as well).
- [0] : https://github.com/gomlx/gomlx - [1] : https://github.com/gomlx/onnx-gomlx
I was doing a Dart wrapper for MXC* this week, and found it was doing telemetry, though IIRC it was forthrightly/clearly documented.
Been on this planet long enough that I've seen plenty of MBAs saying "hoover every piece of data every time we can" and eng going along without thinking or saying anything.
I'm still somewhat surprised Microsoft would do that in SDKs.
* tl;dr: MS' CLI sandbox a la bubblewrap
It's a bit disappointing to me that software which I expect to be fully offline, sometimes isn't.
The flag/telemetry client doesn't exist on v1.28.0, and when I tested on v1.29.0, v1.30.0, v1.31.0, v1.31.1 and v1.32.0 running on MacOS, all built from source locally at those various checkpoints, I don't see the any of the telemetry infrastructure built (device ID is unset, no network queue created, no network session storage created).
Could you provide more context on what the issue here was/is? I might be missing it.
https://mvnrepository.com/artifact/com.microsoft.onnxruntime...
https://github.com/microsoft/agent-framework/
The gpu work was mostly handed of e.g to TensorRT and that also seems since the push for more general LLM models have not really improved.
[0] https://socket.dev/blog/agent-framework-pypi-package-comprom...
[1] https://github.com/microsoft/agent-framework
If you were looking for fewer assumptions then the conclusion would just be that an exploit got missed during the PR step.
Distribution packages no longer build.
I think it's because of this
[0] - https://opensource.googleblog.com/2026/11/supercharging-xla-... [1] - https://xla-serving.readthedocs.io/en/latest/
[0] https://www.theregister.com/security/2026/11/18/microsofts-o...
https://www.theregister.com/security/2026/11/18/microsofts-o...