meta-pytorch / superblockLinks
A block oriented training approach for inference time optimization.
☆34Updated last year
Alternatives and similar repositories for superblock
Users that are interested in superblock are comparing it to the libraries listed below
Sorting:
- This repository contains the experimental PyTorch native float8 training UX☆224Updated last year
- ☆159Updated 2 years ago
- Experiment of using Tangent to autodiff triton☆81Updated last year
- Memory Optimizations for Deep Learning (ICML 2023)☆107Updated last year
- Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops☆30Updated last year
- Patch convolution to avoid large GPU memory usage of Conv2D☆92Updated 7 months ago
- A library for unit scaling in PyTorch☆130Updated 2 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆46Updated last year
- Official implementation for Training LLMs with MXFP4☆91Updated 4 months ago
- extensible collectives library in triton☆87Updated 5 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- ☆118Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆185Updated 3 months ago
- ring-attention experiments☆152Updated 11 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.☆51Updated 2 years ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆111Updated 11 months ago
- ☆82Updated 7 months ago
- Collection of kernels written in Triton language☆154Updated 5 months ago
- The evaluation framework for training-free sparse attention in LLMs☆93Updated 3 months ago
- ☆111Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Updated 11 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆223Updated this week
- ☆94Updated 3 weeks ago
- ☆158Updated 2 years ago
- ☆142Updated 7 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆233Updated 2 weeks ago
- ☆52Updated last year
- Applied AI experiments and examples for PyTorch☆294Updated 3 weeks ago
- ☆56Updated last year