FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA.
-
Updated
Apr 22, 2026 - Cuda
#
tensor-cores
Here are 24 public repositories matching this topic...
⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
-
Updated
May 10, 2025 - Cuda
General Matrix Multiplication using NVIDIA Tensor Cores
matrix-multiplication cuda-kernels gpu-computing nvidia-cuda nvidia-gpu gpu-programming sgemm cuda-programming tensor-cores nvidia-tensor-cores
-
Updated
Jan 25, 2025 - Cuda
CUDA matrix multiplication benchmarking on Jetson Orin Nano. Four implementations, three power modes, five matrix sizes. 99.5% mathematical validation. C++/CUDA and Python.
machine-learning robotics cuda cublas scientific-computing matrix-multiplication high-performance-computing gpu-computing performance-optimization autonomous-systems edge-computing nvidia-jetson edge-ai embeded-systems tensor-cores ml-deployment jetson-orin-nano gpu-benchmarking power-efficiency-benchmark cuda-optimization
-
Updated
Apr 2, 2026 - Python
Vulkan & GLSL implementation of FlashAttention-2
vulkan glsl artificial-intelligence gpu-acceleration attention gpu-computing deel-learning tensor-cores large-language-models llm flash-attention flash-attention-2
-
Updated
Jan 19, 2025 - C++
CUDA 12-first backend inference for Unsloth on Kaggle — Optimized for small GGUF models (1B-5B) on dual Tesla T4 GPUs (15GB each, SM 7.5)
python machine-learning ai deep-learning jupyter gpu cuda inference pytorch nvidia cuda-kernels google-colab tensor-cores tesla-t4 llm gguf unsloth flashattention
-
Updated
Feb 1, 2026 - Jupyter Notebook
A benchmarking framework for correlators of FX telescope arrays
-
Updated
Oct 20, 2023 - Cuda
Progressive CUDA SGEMM tutorial and reference code: five kernels from naive GEMM to Tensor Core WMMA, with cuBLAS verification and benchmarks.
tutorial cuda matrix-multiplication high-performance-computing cuda-kernels shared-memory gemm sgemm gpu-optimization bank-conflict tensor-cores wmma
-
Updated
Apr 22, 2026 - Cuda
Neural Network C is an advanced neural network implementation in pure C, optimized for high performance on CPUs and NVIDIA GPUs.
machine-learning encryption deep-learning neural-network openmp mpi parallel-computing cuda transformers artificial-intelligence high-performance-computing convolutional-neural-networks gpu-computing quantization bayesian-optimization multi-gpu c-programming real-time-monitoring secure-computing tensor-cores
-
Updated
Mar 29, 2025 - C
🎓 CUDA HPC Kernel Optimization Lab: Progressive GEMM, FlashAttention, Tensor Core & CUDA 13 Features | 从朴素到 Tensor Core 的 CUDA 高性能算子优化实验室
machine-learning deep-learning hpc cuda nvidia high-performance-computing hopper cuda-kernels gpu-computing ampere gemm cpp20 gpu-programming gpu-performance tensor-cores ai-inference tensor-core flashattention kernel-optimization cuda-optimization
-
Updated
Apr 22, 2026 - Cuda
High-performance CUDA kernels with step-by-step optimization, profiling, and analysis. A growing collection of GPU solutions demonstrating warp-level tuning, memory optimization, and Tensor Core acceleration.
-
Updated
Nov 12, 2025 - Cuda
INT8 Sparse Tensor Core GEMM for PyTorch — built for Windows
windows gpu cuda inference pytorch nvidia sparse quantization gemm int8 ptx structured-sparsity tensor-cores vram-optimization
-
Updated
Feb 16, 2026 - Cuda
The MNIST classification problem is a fundamental machine learning task that involves recognizing handwritten digits (0- 9) from a dataset of 70,000 grayscale images (28x28 pixels each). It serves as a benchmark for evaluating machine learning models, particularly neural networks.
benchmarking deep-learning parallel-computing cuda mnist neural-networks high-performance-computing gpu-acceleration profiling shared-memory openacc performance-optimization c-cpp nsight tensor-cores cuda-streams pinned-memory
-
Updated
Sep 12, 2025 - Cuda
🔍 Analyze CUDA matrix multiplication performance and power consumption on NVIDIA Jetson Orin Nano across multiple implementations and settings.
machine-learning robotics cuda cublas matrix-multiplication high-performance-computing gpu-computing performance-optimization autonomous-systems edge-computing nvidia-jetson embeded-systems tensor-cores ml-deployment jetson-orin-nano gpu-benchmarking power-efficiency-benchmark cuda-optimization
-
Updated
Apr 23, 2026 - Python
TsuruTune is a comprehensive deep learning model optimization tool designed specifically for NVIDIA Jetson platforms and edge devices.. It leverages Tensor Core acceleration and memory bandwidth alignment to achieve optimal performance for deep learning inference on edge devices.
-
Updated
Jan 8, 2026 - Python
GNN inference acceleration with TVM compiler
-
Updated
Dec 17, 2025 - Python
10,000-image LeNet-5 forward pass in ~28 ms on a single A40 via fused convolution and Tensor Cores (TF32).
parallel-computing cuda inference cnn matrix-multiplication lenet convolution gpu-computing ampere gpu-programming lenet-5 im2col cuda-programming tensor-cores kernel-optimization tf32 wmma
-
Updated
Apr 16, 2026 - Cuda
-
Updated
Apr 20, 2025 - Cuda
CUDA matrix library for GEMM, GEMV, TRSM with naive, tiled, register-blocked, and tensor-core kernels. Includes FP16/BF16 mixed precision, sparse ops, cuSOLVER wrappers, and Python bindings.
-
Updated
Apr 15, 2026 - C++
CUDA GEMM Optimization Learning Project: 7-Level Progressive Optimization from Naive to ~89% cuBLAS Performance | CUDA GEMM 渐进式优化学习项目：7级优化从基础到~89% cuBLAS性能
deep-learning cpp hpc cuda inference nvidia matrix-multiplication high-performance-computing cuda-kernels gpu-computing gemm performance-optimization nvidia-cuda inference-engine gpu-programming cuda-programming tensor-cores
-
Updated
Apr 22, 2026 - C++
Improve this page
Add a description, image, and links to the tensor-cores topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the tensor-cores topic, visit your repo's landing page and select "manage topics."