microsoft / TileFusionLinks
TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
☆90Updated 2 weeks ago
Alternatives and similar repositories for TileFusion
Users that are interested in TileFusion are comparing it to the libraries listed below
Sorting:
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 4 months ago
- ☆60Updated last month
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆80Updated last month
- ☆63Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 11 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 9 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆77Updated this week
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆62Updated 9 months ago
- An extension library of WMMA API (Tensor Core API)☆99Updated 11 months ago
- GPTQ inference TVM kernel☆40Updated last year
- ☆81Updated 7 months ago
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆50Updated 11 months ago
- DeeperGEMM: crazy optimized version☆69Updated last month
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆47Updated 2 weeks ago
- ☆96Updated 9 months ago
- A language and compiler for irregular tensor programs.☆142Updated 6 months ago
- ☆90Updated 5 months ago
- ☆19Updated 8 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆54Updated this week
- extensible collectives library in triton☆86Updated 2 months ago
- Artifacts of EVT ASPLOS'24☆26Updated last year
- ☆71Updated last month
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated 3 weeks ago
- A lightweight design for computation-communication overlap.☆143Updated this week
- Benchmark code for the "Online normalizer calculation for softmax" paper☆94Updated 6 years ago
- Ahead of Time (AOT) Triton Math Library☆66Updated this week
- ☆43Updated 3 weeks ago
- Implement Flash Attention using Cute.☆87Updated 6 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆136Updated this week
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆138Updated 2 years ago