sm75

Here are 4 public repositories matching this topic...

JohnScheuer / llm-fusion-compiler

Compiler MVP that detects Transformer fusion patterns, generates optimized CUDA kernels with WMMA Tensor Cores, and executes them on real GPU hardware — 10.5 TFLOPs on RTX 2070, correctness validated against PyTorch.

Updated Jul 26, 2026
Python

JohnScheuer / fused-backward-kernels-sm75

Star

Backward pass CUDA kernels for fused GEMM+Bias+GeLU on SM75 (Turing). Float4 vectorized WMMA kernels validated against PyTorch autograd. 3.1x faster than autograd at M=1024. 24/24 tests passing.

deep-learning cuda pytorch transformer cuda-kernels turing gemm fp16 gpu-programming gelu wmma backward-pass sm75

Updated Jul 27, 2026
Python

JohnScheuer / flash-attention-sm75

Star

FlashAttention v1 forward pass in CUDA for NVIDIA Turing (SM75)

deep-learning cuda pytorch attention gpu-computing turing tensor-cores llm flash-attention machine-learning-infrastructure wmma sm75

Updated Jul 27, 2026
Python

JohnScheuer / sm75-tensorcore-microkernel

Star

Instruction-level Tensor Core micro-kernel engineering on SM75 (RTX 2070), including PTX manual emission, shared-memory staging, and hardware-aware auto-tuning.

performance-engineering gpu cuda high-performance-computing microkernel auto-tuning ptx tensor-cores deep-learning-infrastructure sm75

Updated Jun 26, 2026
Cuda

Improve this page

Add a description, image, and links to the sm75 topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the sm75 topic, visit your repo's landing page and select "manage topics."

Learn more