awesome-tensor-compilers
Dask
awesome-tensor-compilers | Dask | |
---|---|---|
9 | 32 | |
2,171 | 12,022 | |
- | 0.6% | |
4.4 | 9.6 | |
4 months ago | about 3 hours ago | |
Python | ||
- | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
awesome-tensor-compilers
-
MatX: Faster Chips for LLMs
> So long as Pytorch only practically works with Nvidia GPUs, everything else is little more than a rounding error.
This is changing.
https://github.com/merrymercy/awesome-tensor-compilers
There are more and better projects that can compile an existing PyTorch codebase into a more optimized format for a range of devices. Triton (which is part of PyTorch) TVM and the MLIR based efforts (like torch-MLIR or IREE) are big ones, but there are smaller fish like GGML and Tinygrad, or more narrowly focused projects like Meta's AITemplate (which works on AMD datacenter GPUs).
Hardware is in a strange place now... It feels like everyone but Cerebras and AMD/Intel was squeezed out, but with all the money pouring in, I think this is temporary.
-
Run Llama2-70B in Web Browser with WebGPU Acceleration
I think this is true of AI compilation in general. Torch MLIR, AITemplate and really everything here fly under the radar.
https://github.com/merrymercy/awesome-tensor-compilers#open-...
-
Ask HN: How to get good as a self taught ML engineer?
> I really want to do some great work and help people.
Have you looked into ML compilation?
https://github.com/merrymercy/awesome-tensor-compilers
IMO there is low hanging fruit in the space between high performance ML compilers/runtimes and the actual projects people use. If you practice porting projects you use to these frameworks, that would give you a massive performance edge.
-
Ask HN: What new programming language(s) are you most excited about?
While not all "languages" persay, I am excited about the various ML compilation efforts:
https://github.com/merrymercy/awesome-tensor-compilers
Modern ML training/inference is inefficient, and lacks any portability. These frameworks are how that changes.
-
Research Papers on ML in Compilers
You might be interested in this: https://github.com/merrymercy/awesome-tensor-compilers
-
The Distributed Tensor Algebra Compiler (2022)
* collection of papers in https://github.com/merrymercy/awesome-tensor-compilers
I also have an interest in the community more widely associated with pandas/dataframes-like languages (e.g. modin/dask/ray/polars/ibis) with substrait/calcite/arrow their choice of IR
- A list of compiler projects and papers for tensor computation and deep learning
- A List of Tensor Compilers
-
C-for-Metal: High Performance SIMD Programming on Intel GPUs
Compiling from high-level lang to GPU is a huge problem, and we greatly appreciate efforts to solve it.
If I understand correctly, this (CM) allows for C-style fine-level control over a GPU device as though it were a CPU.
However, it does not appear to address data transit (critical for performance). Compilation and operator fusing to minimize transit is possibly more important. See Graphcore Poplar, Tensorflow XLA, Arrayfire, Pytorch Glow, etc.
Further, this obviously only applies to Intel GPUs, so investing time in utilizing low-level control is possibly a hardware dead-end.
Dream world for programmers is one where data transit and hardware architecture are taken into account without living inside a proprietary DSL Conversely, it is obviously against hardware manufacturers' interests to create this.
Is MLIR / LLVM going to solve this? This list has been interesting to consider:
https://github.com/merrymercy/awesome-tensor-compilers
Dask
- The Distributed Tensor Algebra Compiler (2022)
-
A peek into Location Data Science at Ola
Data scientists work on phenomenally large datasets, and Dask is a handy tool for exploration within the confines of a single cloud VM or their local PCs. Location data visualization is an essential part of deciding further algorithm development and roadmap for projects. This lays the foundation for data engineering and science to work at scale, with petabytes of data.
- File format for large data with many columns
-
What is the best way to save a csv.file in number only ? PC hangs when my file is more than 2GB
Dask
-
Large Scale Hydrology: Geocomputational tools that you use
We're using a lot of Python. In addition to these, gridMET, Dask, HoloViz, and kerchunk.
-
msgspec - a fast & friendly JSON/MessagePack library
I wrote this for speeding up the RPC messaging in dask, but figured it might be useful for others as well. The source is available on github here: https://github.com/jcrist/msgspec.
-
What does it mean to scale your python powered pipeline?
Dask: Distributed data frames, machine learning and more
-
Data pipelines with Luigi
To do that, we are efficiently using Dask, simply creating on-demand local (or remote) clusters on task run() method:
-
Is Numpy always more efficient than Pandas? And how much should we rely on Python anyway?
Look into Dask, see: https://dask.org/
-
Ask HN: Is PySPark a Dead-End?
[1] https://dask.org/
What are some alternatives?
Arraymancer - A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends
Airflow - Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
alpa - Training and serving large-scale neural networks with auto parallelization.
Numba - NumPy aware dynamic Python compiler using LLVM
Fable - The project has moved to a separate organization. This project provides redirect for old Fable web site.
Kedro - Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.
Distributed-Systems-Guide - Distributed Systems Guide
NetworkX - Network Analysis in Python
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
Pandas - Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
tvm - Open deep learning compiler stack for cpu, gpu and specialized accelerators
Interactive Parallel Computing with IPython - IPython Parallel: Interactive Parallel Computing in Python