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.
henryteeare 3 hours ago [-]
onnxruntime.disable_telemetry_events() works doesn't it?
mscdex 3 hours ago [-]
Same with setting `ORT_DISABLE_TELEMETRY=1` in the environment before loading the library.
nullpoint420 2 hours ago [-]
Not to be that guy but I don't think this is the gotcha y'all think it is. I didn't know that ONNX had telemetry.
edit: I seem to have misunderstood the intent of the parent comments. Apologies
I'm just passing information for anyone who wants to disable it without recompiling anything.
refulgentis 1 hours ago [-]
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.
numpad0 5 hours ago [-]
Isn't ONNX itself not MS specific?
tadfisher 4 hours ago [-]
They probably mean "ONNX Runtime", which has unfortunately become synonymous with ONNX-the-standard.
plagiarist 5 hours ago [-]
Yikes. Another bad actor who thinks they are entitled to data.
tclancy 2 hours ago [-]
Much like ham radio.
spdustin 7 hours ago [-]
I wonder if they found new vectors that backdoor'ed models could exploit, like that discussed in the most recent Phrack [^0]
> 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.
6 hours ago [-]
Heliodex 6 hours ago [-]
The closest/furthest ahead fork I could find is https://github.com/intel/onnxruntime for anyone else needing it, though that's with Intel's OpenVINO modifications
Note to people downloading these archives, there is a high likelihood that they contain malware.
nvader 7 hours ago [-]
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?
FesterCluck 7 hours ago [-]
Probably being used in supply chains, and got attacked.
robjam 7 hours ago [-]
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).
quietbritishjim 6 hours ago [-]
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.
7 hours ago [-]
Neywiny 7 hours ago [-]
Why do you think star amount has anything to do with ability to go dark?
tclancy 2 hours ago [-]
From a pure lumens perspective it seems obvious.
binsquare 7 hours ago [-]
it's called "Open Neural Network Exchange (ONNX)", perhaps microsoft is taking a page from OpenAI on what open meanings.
giancarlostoro 5 hours ago [-]
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...
dangoodmanUT 6 hours ago [-]
This is why we vendor everything.
You never know when it's going to vanish
rtpg 5 hours ago [-]
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.
pjmlp 48 minutes ago [-]
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.
rwiggins 5 hours ago [-]
Doesn't Artifactory provide exactly that? Along with having a bunch of features that are generally the right things.
Though I'm pretty sure their enterprise pricing is "give us a call." Maybe your last sentence was a nod to this.
If it were me, I would take the hint and maybe not trust a vendored version right now?
cjbgkagh 5 hours ago [-]
I believe vendoring in this context means forking it and serving it from your own repo.
katbyte 3 hours ago [-]
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
kenferry 3 hours ago [-]
But if we think they took it down because of security issues…
Gluber 2 hours ago [-]
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.
gabriela_c 3 hours ago [-]
As a former (tiny patch, pre-AI) contributor, didn't they have a license that requires everybody's approval to do this?
Arainach 2 hours ago [-]
No. Even if a license required all contributors to agree to change the license, there's no requirement to keep it available on Github.
UncleOxidant 6 hours ago [-]
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.
It convert ONNX models into native, backend-agnostic Burn code for inference and fine-tuning.
ytxm 5 hours ago [-]
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
antimora 5 hours ago [-]
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).
these 4 hours ago [-]
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.
Maybe related to the recent release of MAI? Or the Microsoft AI models?
proc0 6 hours ago [-]
omg, I just built something depending on this. Hopefully the web version is still cached in NPM.
craigacp 5 hours ago [-]
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.
anon291 1 hours ago [-]
Better delete all the open source matrix multipliers because we're making it illegal
[0] https://socket.dev/blog/agent-framework-pypi-package-comprom...
[1] https://github.com/microsoft/agent-framework
Source: https://opensourcemalware.com/blog/agent-framework-pypi-comp...
edit: I seem to have misunderstood the intent of the parent comments. Apologies
[0]: https://phrack.org/issues/73/backdoor-attacks-against-machin...
Does anyone know why or how a repository with 22k stars just went dark?
You never know when it's going to vanish
Of course I wouldn't pay _that_ much money for it.
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.
Though I'm pretty sure their enterprise pricing is "give us a call." Maybe your last sentence was a nod to this.
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.
I maintain this project at the moment.
It convert ONNX models into native, backend-agnostic Burn code for inference and fine-tuning.
> 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...
https://github.com/microsoft/agent-framework/
https://mvnrepository.com/artifact/com.microsoft.onnxruntime...