muriloboratto / NCCL
Sample examples of how to call collective operation functions on multi-GPU environments. A simple example of using broadcast, reduce, allGather, reduceScatter and sendRecv operations.
☆33Updated last year
Alternatives and similar repositories for NCCL
Users that are interested in NCCL are comparing it to the libraries listed below
Sorting:
- Optimize GEMM with tensorcore step by step☆26Updated last year
- ☆109Updated last week
- Matrix Multiply-Accumulate with CUDA and WMMA( Tensor Core)☆131Updated 4 years ago
- ☆68Updated 3 weeks ago
- ☆119Updated 5 months ago
- ☆62Updated 4 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆61Updated 8 months ago
- An extension library of WMMA API (Tensor Core API)☆96Updated 10 months ago
- ☆76Updated 4 months ago
- NCCL Examples from Official NVIDIA NCCL Developer Guide.☆17Updated 6 years ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆76Updated last week
- ☆96Updated last year
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆88Updated 2 years ago
- ☆15Updated 5 years ago
- A practical way of learning Swizzle☆19Updated 3 months ago
- ☆51Updated 5 years ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆73Updated 2 weeks ago
- Dissecting NVIDIA GPU Architecture☆94Updated 2 years ago
- GEMM by WMMA (tensor core)☆12Updated 2 years ago
- Examples and exercises from the book Programming Massively Parallel Processors - A Hands-on Approach. David B. Kirk and Wen-mei W. Hwu (T…☆66Updated 4 years ago
- play gemm with tvm☆91Updated last year
- Examples of CUDA implementations by Cutlass CuTe☆177Updated 3 months ago
- Some source code about matrix multiplication implementation on CUDA☆34Updated 6 years ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆181Updated 3 months ago
- ☆79Updated 6 months ago
- A lightweight design for computation-communication overlap.☆113Updated last week
- Benchmark code for the "Online normalizer calculation for softmax" paper☆91Updated 6 years ago
- ☆25Updated 3 months ago
- ☆38Updated 5 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆36Updated 2 months ago