Pinned Loading

1. LeetCUDA LeetCUDA Public

   📚LeetCUDA: 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.

   Cuda 4.8k 519

2. lite.ai.toolkit lite.ai.toolkit Public

   🛠 A lite C++ AI toolkit: 100+🎉 models with MNN, ORT and TRT.

   C++ 4.1k 743

3. Awesome-LLM-Inference Awesome-LLM-Inference Public

   📚A curated list of Awesome LLM Inference Papers with Codes.

   Python 4.1k 287

4. torchlm torchlm Public

   💎An easy-to-use PyTorch library for face landmarks detection.

   Python 260 24

5. Awesome-DiT-Inference Awesome-DiT-Inference Public

   📚A curated list of Awesome DiT Inference Papers with Codes.

   261 16

6. ffpa-attn ffpa-attn Public

   📚FFPA: Extend FA-2 with Split-D for large headdim, 2x↑ vs SDPA.

   Cuda 186 8