chsasank / device-benchmarks
Benchmarks of different devices I have come across
☆17Updated last month
Alternatives and similar repositories for device-benchmarks:
Users that are interested in device-benchmarks are comparing it to the libraries listed below
- SGEMM that beats cuBLAS☆68Updated last week
- LLM training in simple, raw C/CUDA☆91Updated 8 months ago
- Learning about CUDA by writing PTX code.☆33Updated 11 months ago
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆38Updated 8 months ago
- extensible collectives library in triton☆77Updated 4 months ago
- TORCH_LOGS parser for PT2☆30Updated this week
- ☆64Updated 2 months ago
- An experimental CPU backend for Triton☆81Updated last week
- Fast low-bit matmul kernels in Triton☆199Updated last week
- Small scale distributed training of sequential deep learning models, built on Numpy and MPI.☆116Updated last year
- ☆171Updated last week
- MLIR-based partitioning system☆58Updated this week
- ☆21Updated 3 months ago
- Collection of kernels written in Triton language☆91Updated 3 months ago
- Make triton easier☆44Updated 7 months ago
- The simplest but fast implementation of matrix multiplication in CUDA.☆34Updated 6 months ago
- SandLogic Lexicons☆17Updated 3 months ago
- ☆85Updated 11 months ago
- Inference Vision Transformer (ViT) in plain C/C++ with ggml☆247Updated 9 months ago
- Machine Learning Agility (MLAgility) benchmark and benchmarking tools☆38Updated last month
- Experiment of using Tangent to autodiff triton☆74Updated last year
- Cataloging released Triton kernels.☆157Updated 3 weeks ago
- An implementation of the transformer architecture onto an Nvidia CUDA kernel☆167Updated last year
- ☆48Updated 10 months ago
- Custom kernels in Triton language for accelerating LLMs☆17Updated 9 months ago
- ☆24Updated 2 weeks ago
- Learn CUDA with PyTorch☆16Updated this week
- ☆279Updated last week
- ☆34Updated this week
- ☆49Updated 5 months ago