microsoft / TileFusion
TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing. By providing a higher-level interface, algorithm developers can design hardware-aware algorithms without dealing with low-level hardware complexities.
☆68Updated this week
Alternatives and similar repositories for TileFusion:
Users that are interested in TileFusion are comparing it to the libraries listed below
- GPTQ inference TVM kernel☆39Updated 10 months ago
- ☆19Updated 5 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆63Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆100Updated 8 months ago
- ☆73Updated 4 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆177Updated last month
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆59Updated 2 weeks ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆106Updated 6 months ago
- Implement Flash Attention using Cute.☆71Updated 3 months ago
- ☆87Updated last week
- Artifacts of EVT ASPLOS'24☆24Updated last year
- ☆24Updated 3 months ago
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆51Updated 7 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆57Updated 6 months ago
- ☆55Updated 2 months ago
- extensible collectives library in triton☆83Updated 5 months ago
- ☆87Updated 6 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆89Updated 3 weeks ago
- play gemm with tvm☆89Updated last year
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆135Updated last year
- ☆42Updated 2 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆60Updated 7 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆104Updated this week
- ThrillerFlow is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated 3 months ago
- An extension library of WMMA API (Tensor Core API)☆91Updated 8 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆73Updated 4 months ago
- llama INT4 cuda inference with AWQ☆53Updated 2 months ago
- Triton to TVM transpiler.☆18Updated 5 months ago