maxas
triton
| maxas | triton | |
|---|---|---|
| 3 | 30 | |
| 784 | 11,054 | |
| - | 4.3% | |
| 0.0 | 9.9 | |
| over 1 year ago | 3 days ago | |
| Sass | C++ | |
| MIT License | MIT 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.
maxas
- With LLVM and MLIR, is manual cuda optimizing still important?
-
How to make CUDA libraries more performant?
cuDNN is already very optimized but if you want to read on optimizing, here you go (Maxwell specifix) https://github.com/NervanaSystems/maxas/wiki/SGEMM, there is an accompanying paper or read Nvidia Cutlass.
-
Image convolution optimisation strategies.
As explained in https://github.com/NervanaSystems/maxas/wiki/SGEMM you need to do the same on GPUs.
triton
- OpenAI Triton: language and compiler for highly efficient Deep-Learning
-
Show HN: Ollama for Linux – Run LLMs on Linux with GPU Acceleration
There's a ton of cool opportunity in the runtime layer. I've been keeping my eye on the compiler-based approaches. From what I've gathered many of the larger "production" inference tools use compilers:
- https://github.com/openai/triton
- Core Functionality for AMD #1983
- Project name easily confused with Nvidia triton
-
Nvidia's CUDA Monopoly
Does anyone have more inside knowledge from OpenAI or AMD on AMDGPU support for Triton?
I see this:
https://github.com/openai/triton/issues/1073
But it's not clear to me if we will see AMD GPUs as first class citizens for pytorch in the future?
- @soumithchintala (Cofounded and lead @PyTorch at Meta) on Twitter: I'm fairly puzzled by $NVDA skyrocketing... (cont.)
-
The tiny corp raised $5.1M
I thought this was a good overview of the idea Triton can circumvent the CUDA moat: https://www.semianalysis.com/p/nvidiaopenaitritonpytorch
It also looks like they added MLIR backend to Triton though I wonder if Mojo has advantages since it was built on MLIR? https://github.com/openai/triton/pull/1004
-
Anyone hosting a local LLM server
I'm pretty happy with the setup, because it allows me to keep all the AI stuff and its dozens of conda envs and repos etc. seperate from my normal setup and "portable". It may have some performance impact (although I don't personally notice any significant difference to running it "natively" on windows), and it may enable some extra functionality, such as access to OpenAi's Triton etc., but that's currently neither here nor there.
- Triton: Runtime for highly efficient custom Deep-Learning primitives
-
Mojo – a new programming language for all AI developers
Very cool development. There is too much busy work going from development to test to production. This will help to unify everything. OpenAI Triton https://github.com/openai/triton/ is going for a similar goal. But this is a more fundamental approach.
What are some alternatives?
Halide - a language for fast, portable data-parallel computation
cuda-python - CUDA Python Low-level Bindings
blislab - BLISlab: A Sandbox for Optimizing GEMM
Image-Convolutaion-OpenCL
GPU-Puzzles - Solve puzzles. Learn CUDA.
cutlass - CUDA Templates for Linear Algebra Subroutines
dfdx - Deep learning in Rust, with shape checked tensors and neural networks
web-llm - Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
gptq - Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".