#
Lists (2)
Starred repositories
9
results
for source starred repositories
written in Cuda
Clear filter
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
FlashInfer: Kernel Library for LLM Serving
GPU Accelerated t-SNE for CUDA with Python bindings
Causal depthwise conv1d in CUDA, with a PyTorch interface
🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
Sample code from the book "Professional CUDA C Programming"