pytorch-labs / tritonbench
Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
☆111Updated this week
Alternatives and similar repositories for tritonbench:
Users that are interested in tritonbench are comparing it to the libraries listed below
- PyTorch bindings for CUTLASS grouped GEMM.☆81Updated 5 months ago
- extensible collectives library in triton☆85Updated 3 weeks ago
- ☆103Updated 7 months ago
- ☆78Updated 5 months ago
- Applied AI experiments and examples for PyTorch☆261Updated last month
- DeeperGEMM: crazy optimized version☆67Updated 3 weeks ago
- ☆157Updated last year
- Fast low-bit matmul kernels in Triton☆291Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆106Updated 9 months ago
- This repository contains the experimental PyTorch native float8 training UX☆223Updated 8 months ago
- Collection of kernels written in Triton language☆119Updated 2 weeks ago
- ☆200Updated this week
- ☆68Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆72Updated 7 months ago
- ☆198Updated 9 months ago
- Cataloging released Triton kernels.☆217Updated 3 months ago
- ☆92Updated 7 months ago
- ring-attention experiments☆130Updated 6 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆116Updated last year
- ☆55Updated last week
- Odysseus: Playground of LLM Sequence Parallelism☆68Updated 10 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆63Updated last week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆81Updated 2 weeks ago
- ☆82Updated 3 weeks ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆91Updated 6 years ago
- Triton-based implementation of Sparse Mixture of Experts.☆210Updated 4 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆174Updated 11 months ago
- ☆66Updated 3 months ago
- ☆122Updated 2 months ago
- A bunch of kernels that might make stuff slower 😉☆34Updated this week