meta-pytorch / BackendBenchLinks
How to ensure correctness and ship LLM generated kernels in PyTorch
☆66Updated last week
Alternatives and similar repositories for BackendBench
Users that are interested in BackendBench are comparing it to the libraries listed below
Sorting:
- extensible collectives library in triton☆89Updated 6 months ago
- Triton-based Symmetric Memory operators and examples☆38Updated last week
- Write a fast kernel and run it on Discord. See how you compare against the best!☆58Updated last week
- ring-attention experiments☆154Updated last year
- Collection of kernels written in Triton language☆157Updated 6 months ago
- ☆92Updated 11 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆264Updated this week
- Framework to reduce autotune overhead to zero for well known deployments.☆84Updated last month
- ☆112Updated last year
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆160Updated last week
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- Fast low-bit matmul kernels in Triton☆381Updated 3 weeks ago
- ☆240Updated this week
- TPU inference for vLLM, with unified JAX and PyTorch support.☆97Updated this week
- PyTorch bindings for CUTLASS grouped GEMM.☆124Updated 4 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆133Updated last month
- Applied AI experiments and examples for PyTorch☆299Updated 2 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆246Updated 3 weeks ago
- Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Lar…☆68Updated 3 weeks ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 3 months ago
- Cataloging released Triton kernels.☆263Updated last month
- JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training☆55Updated last week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆215Updated last week
- AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming☆91Updated this week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆119Updated 3 weeks ago
- ☆218Updated 9 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆83Updated last year
- ☆65Updated 5 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆351Updated last week
- This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".☆69Updated 3 weeks ago