tspeterkim / mixed-precision-from-scratch
Mixed precision training from scratch with Tensors and CUDA
☆21Updated 10 months ago
Alternatives and similar repositories for mixed-precision-from-scratch:
Users that are interested in mixed-precision-from-scratch are comparing it to the libraries listed below
- ring-attention experiments☆127Updated 4 months ago
- Cataloging released Triton kernels.☆191Updated 2 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆58Updated last month
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆103Updated this week
- ☆148Updated last year
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆68Updated 9 months ago
- This repository contains the experimental PyTorch native float8 training UX☆222Updated 7 months ago
- Experiment of using Tangent to autodiff triton☆76Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆59Updated 5 months ago
- ☆67Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆68Updated 6 months ago
- Fast low-bit matmul kernels in Triton☆257Updated last week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆231Updated 2 weeks ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆123Updated 3 months ago
- ☆115Updated last month
- ☆188Updated 3 weeks ago
- ☆75Updated 8 months ago
- A minimal implementation of vllm.☆35Updated 7 months ago
- Code for studying the super weight in LLM☆91Updated 3 months ago
- extensible collectives library in triton☆83Updated 5 months ago
- a minimal cache manager for PagedAttention, on top of llama3.☆71Updated 6 months ago
- Small scale distributed training of sequential deep learning models, built on Numpy and MPI.☆125Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆121Updated 7 months ago
- ☆94Updated 9 months ago
- Make triton easier☆47Updated 9 months ago
- ☆46Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆62Updated 2 weeks ago
- Learn CUDA with PyTorch☆18Updated last month
- Collection of kernels written in Triton language☆110Updated 3 weeks ago