Snektron / gpumode-amd-fp8-mmLinks
My submission for the GPUMODE/AMD fp8 mm challenge
☆29Updated 4 months ago
Alternatives and similar repositories for gpumode-amd-fp8-mm
Users that are interested in gpumode-amd-fp8-mm are comparing it to the libraries listed below
Sorting:
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆15Updated 3 weeks ago
- Learning about CUDA by writing PTX code.☆138Updated last year
- Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X☆69Updated 2 months ago
- PTX-Tutorial Written Purely By AIs (Deep Research of Openai and Claude 3.7)☆66Updated 6 months ago
- High-Performance SGEMM on CUDA devices☆105Updated 8 months ago
- ☆98Updated last month
- Quantized LLM training in pure CUDA/C++.☆32Updated last week
- pytorch from scratch in pure C/CUDA and python☆41Updated 11 months ago
- TritonParse: A Compiler Tracer, Visualizer, and mini-Reproducer for Triton Kernels☆152Updated this week
- coding CUDA everyday!☆61Updated 5 months ago
- Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!☆97Updated last week
- Custom PTX Instruction Benchmark☆128Updated 7 months ago
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆226Updated 5 months ago
- Write a fast kernel and run it on Discord. See how you compare against the best!☆57Updated last week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆99Updated 3 weeks ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆324Updated 3 weeks ago
- AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming☆82Updated this week
- Experimental GPU language with meta-programming☆23Updated last year
- General Matrix Multiplication using NVIDIA Tensor Cores☆21Updated 8 months ago
- ☆21Updated 2 months ago
- Samples of good AI generated CUDA kernels☆90Updated 4 months ago
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆369Updated last week
- ☆30Updated 3 months ago
- making the official triton tutorials actually comprehensible☆54Updated last month
- ☆90Updated 11 months ago
- ☆42Updated 3 weeks ago
- It is an LLM-based AI agent, which can write correct and efficient gpu kernels automatically.☆32Updated last month
- How to ensure correctness and ship LLM generated kernels in PyTorch☆66Updated this week
- ☆78Updated 2 weeks ago
- Hand-Rolled GPU communications library☆34Updated last week