lessw2020 / triton_kernels_for_fun_and_profit
Custom kernels in Triton language for accelerating LLMs
☆14Updated 5 months ago
Related projects: ⓘ
- ML/DL Math and Method notes☆56Updated 9 months ago
- A place to store reusable transformer components of my own creation or found on the interwebs☆43Updated 3 weeks ago
- Simple and fast low-bit matmul kernels in CUDA☆48Updated this week
- Small scale distributed training of sequential deep learning models, built on Numpy and MPI.☆88Updated 11 months ago
- Personal solutions to the Triton Puzzles☆11Updated 2 months ago
- This is a port of Mistral-7B model in JAX☆29Updated 2 months ago
- Experiment of using Tangent to autodiff triton☆66Updated 7 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆34Updated 2 months ago
- Make triton easier☆39Updated 3 months ago
- ☆12Updated last year
- Collection of autoregressive model implementation☆62Updated 2 weeks ago
- PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu☆25Updated 3 weeks ago
- ☆22Updated last week
- Learn CUDA with PyTorch☆11Updated last month
- ☆38Updated 9 months ago
- a Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization in pure C.☆21Updated 2 months ago
- This code repository contains the code used for my "Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorch" blog po…☆84Updated last year
- LLM training in simple, raw C/CUDA☆79Updated 4 months ago
- Cataloging released Triton kernels.☆111Updated 3 weeks ago
- A Learning Journey: Micrograd in Mojo 🔥☆57Updated 3 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆66Updated 3 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆26Updated this week
- ☆25Updated this week
- ☆68Updated 2 months ago
- ☆124Updated last week
- Gpu benchmark☆35Updated 2 weeks ago
- Learning about CUDA by writing PTX code.☆28Updated 6 months ago
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆46Updated 5 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆82Updated 3 weeks ago
- "PyTorch in Rust"☆16Updated 7 months ago