How would this perform compared with Tensorflow?
AITemplate, a revolutionary new inference engine by Meta AI
11–20 of 36 posts
Re: AITemplate, a revolutionary new inference engine by Meta AI
#12Sadly it doesn't have Apple GPU backend
It mentions it is in the works
Re: AITemplate, a revolutionary new inference engine by Meta AI
#13For all the hate that Facebook gets their only redeeming quality is these open source projects they have been releasing all along. Maybe this is to attract better engineers but all in all this has been a net postive for software development. So credit where it is due.
Yes, it's hard to know in the balance whether the net contribution of these advertising companies (fb and google mainly) is a net positive, but their contribution to ML research is unmatched and has created an insane amount of value (I'd speculate rivaling their market caps but someone can probably prove me wrong) in business and research that uses the tools they've built.
Re: AITemplate, a revolutionary new inference engine by Meta AI
#14tl;dr: Meta is open sourcing AITemplate, an inference engine for both Nvidia and AMD GPUs. Code: https://github.com/facebookincubator/AITemplate . AITemplate delivers much better perf (1.9x ~ 12.8x) compared to PyTorch eager on SOTA models, including Bert, ResNet, VIT and StableDiffusion. AITemplate also delivers high perf numbers using AMD GPUs (MI-250). With AITemplate, MI-250 achieves 80% ~ 96% A100 perf on variou…
Thanks, that is very helpful. Do you have to train the model differently for use with AITemplate? Could it be helpful for Leela Chess Zero (LC0)? I think LC0 has a generic Pytorch backend, that is several times slower than its NVidia specific CUDA backend. I'm not very clueful about this stuff though.
No, you don't need to train the model differently to use it with AITemplate. Here is an intro example to do inference with AITemplate with a very simple PyTorch model: https://facebookincubator.github.io/AITemplate/tutorial/how_.... For more advanced examples, check out https://github.com/facebookincubator/AITemplate/tree/main/ex...
Re: AITemplate, a revolutionary new inference engine by Meta AI
#15tl;dr: Meta is open sourcing AITemplate, an inference engine for both Nvidia and AMD GPUs. Code: https://github.com/facebookincubator/AITemplate . AITemplate delivers much better perf (1.9x ~ 12.8x) compared to PyTorch eager on SOTA models, including Bert, ResNet, VIT and StableDiffusion. AITemplate also delivers high perf numbers using AMD GPUs (MI-250). With AITemplate, MI-250 achieves 80% ~ 96% A100 perf on variou…
Thanks, that is very helpful. Do you have to train the model differently for use with AITemplate? Could it be helpful for Leela Chess Zero (LC0)? I think LC0 has a generic Pytorch backend, that is several times slower than its NVidia specific CUDA backend. I'm not very clueful about this stuff though.
As @haolu7 mentioned, you could take a pre-trained model and use AITemplate to do model inference. All you need to do is to re-write the model using AITemplate frontend and map PyTorch params to AITemplate params. Besides, AITemplate has a limited operator coverage compared to mature frameworks like PyTorch so you may need to implement your own kernels if necessary (though it already supports Bert, VIT, StableDiffusion, ResNet, Detectron, and general recommendation models).
Re: AITemplate, a revolutionary new inference engine by Meta AI
#16tl;dr: Meta is open sourcing AITemplate, an inference engine for both Nvidia and AMD GPUs. Code: https://github.com/facebookincubator/AITemplate . AITemplate delivers much better perf (1.9x ~ 12.8x) compared to PyTorch eager on SOTA models, including Bert, ResNet, VIT and StableDiffusion. AITemplate also delivers high perf numbers using AMD GPUs (MI-250). With AITemplate, MI-250 achieves 80% ~ 96% A100 perf on variou…
How did AITemplate performance to state of art inference engine like tvm or onnx runtime ? Did AITemplate optimize/quantify network?
Edit: link for TVM https://tvm.apache.org/
Re: AITemplate, a revolutionary new inference engine by Meta AI
#17tl;dr: Meta is open sourcing AITemplate, an inference engine for both Nvidia and AMD GPUs. Code: https://github.com/facebookincubator/AITemplate . AITemplate delivers much better perf (1.9x ~ 12.8x) compared to PyTorch eager on SOTA models, including Bert, ResNet, VIT and StableDiffusion. AITemplate also delivers high perf numbers using AMD GPUs (MI-250). With AITemplate, MI-250 achieves 80% ~ 96% A100 perf on variou…
Do you know of any good explanations of the techniques you used for those who only touch PyTorch Eager + occasionally torchscript?
Re: AITemplate, a revolutionary new inference engine by Meta AI
#18AITemplate-PyTorch Stable Diffusion is the fastest stable diffusion inference solution by pushing image generation below one second on A100 (batch 1: 0.7s / 25 steps, 1.3s / 50 steps; batch 3: 1.6s / 25 steps, per image 0.55s; batch 16 7.9s / 25 steps, per image 0.49s) for the first time, 2.57X faster than Keras' XLA-based GPU compilation solution. More benchmark numbers and repro at: https://github.com/facebookincub…
Wow. Considering that with the better samplers you can reduce steps to 10-15, this is getting close to near-instant results.
One or two more optimizations and we're gonna have live-update results.
Re: AITemplate, a revolutionary new inference engine by Meta AI
#19For all the hate that Facebook gets their only redeeming quality is these open source projects they have been releasing all along. Maybe this is to attract better engineers but all in all this has been a net postive for software development. So credit where it is due.
Yes, it's hard to know in the balance whether the net contribution of these advertising companies (fb and google mainly) is a net positive, but their contribution to ML research is unmatched and has created an insane amount of value (I'd speculate rivaling their market caps but someone can probably prove me wrong) in business and research that uses the tools they've built.
The net impact of these companies is massively positive. Facebook, with its trust-engendering social graph, enables huge numbers of businesses and social groups to exist that otherwise couldn't while Google has enabled so much information discovery that we just take for granted now.
Of course I would argue there's a better way to provide these kinds of services that concentrates power less, and that's decentralization with cryptoeconomic incentives to maintain consensus, but for their generation, they did well.
Re: AITemplate, a revolutionary new inference engine by Meta AI
#20tl;dr: Meta is open sourcing AITemplate, an inference engine for both Nvidia and AMD GPUs. Code: https://github.com/facebookincubator/AITemplate . AITemplate delivers much better perf (1.9x ~ 12.8x) compared to PyTorch eager on SOTA models, including Bert, ResNet, VIT and StableDiffusion. AITemplate also delivers high perf numbers using AMD GPUs (MI-250). With AITemplate, MI-250 achieves 80% ~ 96% A100 perf on variou…
How do you verify the correctness of your fusion operation ?