AMD-AGI / torchtitan-amdLinks
A PyTorch native platform for training generative AI models
☆14Updated 2 months ago
Alternatives and similar repositories for torchtitan-amd
Users that are interested in torchtitan-amd are comparing it to the libraries listed below
Sorting:
- COCCL: Compression and precision co-aware collective communication library☆29Updated 10 months ago
- Graph-indexed Pandas DataFrames for analyzing hierarchical performance data☆34Updated last month
- Acceleration codes for the Ozaki-scheme on integer matrix multiplication units.☆17Updated last month
- Sparsity support for PyTorch☆38Updated 10 months ago
- ☆59Updated this week
- ☆20Updated 6 years ago
- Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.☆32Updated 9 months ago
- This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".☆95Updated 4 months ago
- A Symbolic Emulator for Shuffle Synthesis on the NVIDIA PTX Code☆15Updated 2 years ago
- ☆55Updated 2 months ago
- Ahead of Time (AOT) Triton Math Library☆88Updated this week
- AMD HPC Research Fund Cloud☆17Updated last week
- ☆53Updated 8 months ago
- [DEPRECATED] Moved to ROCm/rocm-systems repo☆26Updated last week
- An HPL-AI implementation for Fugaku☆23Updated 4 years ago
- ☆39Updated last month
- Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Lar…☆94Updated 3 weeks ago
- Test suite for probing the numerical behavior of NVIDIA tensor cores☆41Updated last year
- Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs☆13Updated 9 months ago
- 🎃 GPU load-balancing library for regular and irregular computations.☆64Updated 4 months ago
- Distributed SDDMM Kernel☆12Updated 3 years ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆105Updated 7 months ago
- ☆101Updated last year
- Reference implementations of MLPerf™ HPC training benchmarks☆49Updated 11 months ago
- ☆18Updated 2 years ago
- [DEPRECATED] Moved to ROCm/rocm-systems repo☆84Updated last week
- A lightweight triton-based General Matrix Multiplication (GEMM) library.☆42Updated last week
- Parallel framework for training and fine-tuning deep neural networks☆70Updated 2 months ago
- cuASR: CUDA Algebra for Semirings☆44Updated 3 years ago
- MPI accelerator-integrated communication extensions☆39Updated 2 years ago