tgautam03 / tGeMMLinks
General Matrix Multiplication using NVIDIA Tensor Cores
☆24Updated 9 months ago
Alternatives and similar repositories for tGeMM
Users that are interested in tGeMM are comparing it to the libraries listed below
Sorting:
- Custom PTX Instruction Benchmark☆131Updated 8 months ago
- Attention in SRAM on Tenstorrent Grayskull☆38Updated last year
- High-Performance SGEMM on CUDA devices☆109Updated 9 months ago
- Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!☆116Updated last week
- Step by step implementation of a fast softmax kernel in CUDA☆54Updated 10 months ago
- ☆49Updated last month
- Write a fast kernel and run it on Discord. See how you compare against the best!☆61Updated last week
- LLM training in simple, raw C/CUDA☆107Updated last year
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆47Updated 2 months ago
- Learning about CUDA by writing PTX code.☆146Updated last year
- Automatic differentiation for Triton Kernels☆28Updated 2 months ago
- Super fast FP32 matrix multiplication on RDNA3☆78Updated 7 months ago
- ☆22Updated 3 months ago
- ☆47Updated 6 months ago
- NVIDIA tools guide☆145Updated 10 months ago
- Quantized LLM training in pure CUDA/C++.☆214Updated this week
- Personal solutions to the Triton Puzzles☆20Updated last year
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆167Updated last week
- ☆14Updated 8 months ago
- PTX-Tutorial Written Purely By AIs (Deep Research of Openai and Claude 3.7)☆66Updated 7 months ago
- It is an LLM-based AI agent, which can write correct and efficient gpu kernels automatically.☆35Updated 3 months ago
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆16Updated last month
- Examples and exercises from the book Programming Massively Parallel Processors - A Hands-on Approach. David B. Kirk and Wen-mei W. Hwu (T…☆75Updated 4 years ago
- making the official triton tutorials actually comprehensible☆60Updated 2 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆125Updated last week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 4 months ago
- ☆123Updated 2 weeks ago
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Updated 5 months ago
- CUDA Matrix Multiplication Optimization☆235Updated last year
- A Data-Centric Compiler for Machine Learning☆85Updated last year