NVIDIA / online-softmaxLinks
Benchmark code for the "Online normalizer calculation for softmax" paper
☆101Updated 7 years ago
Alternatives and similar repositories for online-softmax
Users that are interested in online-softmax are comparing it to the libraries listed below
Sorting:
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆116Updated last year
- ☆98Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 7 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆67Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 3 weeks ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated last year
- ☆238Updated last year
- 使用 cutlass 仓 库在 ada 架构上实现 fp8 的 flash attention☆75Updated last year
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆186Updated 8 months ago
- ☆106Updated 4 months ago
- llama INT4 cuda inference with AWQ☆55Updated 8 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆119Updated 4 months ago
- ☆144Updated 4 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- play gemm with tvm☆91Updated 2 years ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆97Updated 3 months ago
- ☆109Updated 6 months ago
- ☆43Updated last year
- ☆90Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆123Updated 4 months ago
- Implement Flash Attention using Cute.☆96Updated 9 months ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆49Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆132Updated 2 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆279Updated last year
- ☆121Updated 9 months ago
- ☆56Updated 2 months ago
- ☆151Updated last year
- ☆150Updated 8 months ago
- ☆64Updated 5 months ago
- Matrix Multiply-Accumulate with CUDA and WMMA( Tensor Core)☆143Updated 5 years ago