Jian Chen
Jian Chen
Hi, Pauldog thanks for reaching out. We have received your message and put these requests under consideration! Thank you for your time, Jian Chen (not a A.I.)
Also Could you please provide me more information about your scenarios, like: hardware to you wants to run on, and models you are interested in? Again, out currently priority is...
@xenova @josephrocca The only hardware we know that can support 4 bit quantization with performance gain is Nvidia A100, but we cannot get our hands on enough A100, and the...
Let me rebuild them with trt. ETA EOD.
We are using cuda12.2 as well. PyTorch hasn't supported cuda 12 yet last time I checked.
It will be provided on 1.17.3 release
> > Moving nonessential functions to the onnxruntime/tools/python/util package. Only left function that are meaningful to the build process. > > Can you clarify what "nonessential" means? I gather it's...
> It is good that we support cuda 12 as major (instead of cuda 11) in nightly going forward. > > Any reason that stable diffusion test failed? It is...
All changes from Changes from `gradlew` and `gradlew.bat` are generated by `./gradlew wrapper --gradle-version=8.10.2 --distribution-type=bin`
> This change is surprisingly huge. Because those 2 yarn.lock files are generated by npm. I think it might be better generate them during the CI runtime, instead of committing...