The second part of this sentence is true because the first part is false.

So does perpetual motion :shrug: but my point is Triton is not an abstraction in the least. Source: 1) I spent 6 months investigating targeting other backends 2) Phil himself said he doesn't care to support other backends https://github.com/openai/triton/pull/1797#issuecomment-1730...

Discussing: Transformer [1] memory issues and approximate attention [2] in machine learning training.

Specifically: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. [3]

As a side comment, this entire industry is sorely in need of at least intros. The entire space has moved so fast in the last year I need an entire new dictionary and thesaurus for all the terms they've created. Notably, because of this, found out Google has a glossary of machine learning terms. Actually somewhat handy.

[1] Google Machine Learning Glossary (Transformer): https://developers.google.com/machine-learning/glossary/#tra...

[2] Same (Attention): https://developers.google.com/machine-learning/glossary/#att...

[2] arXiv: https://arxiv.org/abs/2205.14135

Build a GPT using Python and Pytorch. For a good course: Andrej Karpathy is your keyword. At $1000 his course is great value. But actually it is free which is even better ;-)

It wont take you to flash attention but will ramp you to the point you could probably read papers about it. I almost got that far then life lifed me. But I was able to implement changes to the architecture of GPT and do some “hey mum I am doing SOTA (2021) machine learning”.

Although in a couple years, kids in restaurants will probably telling me how they're leveling up attention on their neuro-pet. The singularity is steep.

Last I studied ML was 2016 and that was stuff like decision trees, k nearest neighbors...

Zero shot is testing out if distribution, not just "a task" not trained on. The later is ill defined.

The original definition comes from a few papers. But the classic example is a clarifier recognizing zebras but having never been trained in zebras (but may have been trained on horses). There's are out of distribution. But importantly, out of the implicit distribution, not the target distribution.

The common improper usage usually confuses these two. A simple example might me training in 256x256 images and testing on 1024x1024. That's still in the implicit distribution (as long as the classes are identical). A very common example is training on a large dataset like LAION and then testing on coco or image net 1k. This is not zero shot because the classes in ImageNet are in LAION (and in Coco). Basically, this is a useless definition because then any validation or test set is zero shot because those were never seen in the training data and thus out of the training distribution. But remember that data sets are proxies for larger distributions.

Where is can get sometimes tricky is tasks (emergence has entered the chat). For example, you may not intend to train a generative model to do clarification but you probably did (it's very clear -- in the math -- if you're training density models (KLD, score, etc)). This can get hairy because it's very easy to train a model to do things that you aren't realizing you are and later find out. Some people can get upset about this but it's the nature of frameworks that have low interpretability. There's still a lot of mathematics we need to learn and it tends not to be an explicit focus in ML but there are plenty in the community focused on this.

Since the threads are relying on each other to fill the SRAM with all needed data if you didn’t wait then values would be missing.

There's also explicit warp synchronization, i.e. __syncwarp(). More on warp primitives here: https://developer.nvidia.com/blog/using-cuda-warp-level-prim...

I need to get more comfortable with matrix derivatives before I can confidently reimplement it in the same minimal way as I did with the forward pass.

1. "100 lines of CUDA" + PyTorch; maybe this is useful and maybe it isn't, but counting lines of code on top of a huge codebase is not very meaningful.

2. Launching separate kernels, synchronously, on the default stream, for various operations, is typically not the right way to utilize a GPU.

In this case it's pretty reasonable imo, since the kernel itself is fairly independent - the usage of torch is just for some bindings for the data structures.

> Launching separate kernels, synchronously, on the default stream, for various operations, is typically not the right way to utilize a GPU.

This is actually the standard way to do things in ML. Assuming you're from a HPC background (where this may seem quite strange), the biggest change is that "More or less everything in ML runs on the GPU", so there is very rarely any device to host synchronizations. In addition, each individual kernel is typically run on fairly large chunks of data (a million elements would be on the smaller side), so maximizing occupancy with streams is not as necessary as in HPC.

What does that mean?